Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "2:3", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken outdoors on a grassy hillside in bright midday sunlight, but the flash overpowers the sun, creating deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The sky is heavily darkened but faintly visible, the grass becomes pale greenish‑grey, and the white rabbits appear overexposed with blown highlights. Ultra‑realistic textures of grass, fabric, and rabbit fur – all rendered with natural grain and no smoothing. The composition is dynamic, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, surreal, and whimsical, with a dreamcore, absurdist atmosphere.", "scene": { "location": "A steep grassy hillside on a bright sunny day, but the flash overpowers the sun. The grass is tall (20‑60 cm), vivid green in reality, but appears pale olive‑grey with overexposed patches. Several white rabbits (approximately 4) are scattered across the slope, frozen mid‑action, their white fur blown out with specular highlights. The sky is deep blue originally, but now appears dark grey‑blue with a bright hotspot near the horizon, almost black at the top. A diagonal line runs from the lower left to the upper right, following the slope.", "subject": { "description": "A man in formal clothing, caught mid‑leap, jumping upward and forward along the slope. He is in side profile (facing left), body angled, arms and legs spread dynamically, as if running or dancing in the air. He wears a white short‑sleeve shirt (overexposed, pure white in patches), a black fitted vest (deep charcoal, with bright edges from flash), dark grey trousers (pale grey with harsh shadows), and black dress shoes (dark, reflecting the flash). His face is in profile, expression neutral but slightly intense, eyes visible but with harsh catchlights from the flash. His hair is dark, wind‑blown.", "pose": "Mid‑air, front leg extended downward, back leg horizontal, arms raised and spread with fingers splayed. The body is leaning forward (~10‑15°), head facing direction of motion." }, "animals": { "description": "White rabbits of various sizes, scattered on the grass. Some are sitting, some hopping, their fur overexposed with bright white highlights, shadows underneath them sharp and black. Their eyes reflect the flash with red‑eye effect (typical of 90s compact cameras)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient sunlight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the man's white shirt, the rabbits' fur, and the brightest patches of grass; deep black shadows under the man, under the rabbits, and in the upper sky.", "effects": [ "strong, direct flash creating pure white blown highlights on the white shirt and rabbit fur, with sharp specular reflections", "the sky appears dark grey‑blue, almost black at the top, with a bright circular hotspot near the horizon", "the grass is pale and washed out, with individual blades visible but lacking deep green color", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass is pale olive‑grey, the sky is dark blue‑grey, the black vest appears charcoal, the white shirt is pure white with no detail", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (man's outline, rabbit fur edges, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges", "red‑eye effect on the rabbits (typical of direct flash)" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The green grass becomes pale olive‑grey, the blue sky becomes dark grey‑blue, the white shirt is pure white with a slight cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Low angle (camera below the subject), looking upward at the man, side profile, with the slope rising diagonally from lower left to upper right. Camera distance ~8‑12 m. Wide‑angle lens (~28‑35mm equivalent).", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 28‑35mm equivalent, fixed focus or autofocus with slight softness, aperture f/5.6‑f/8, shutter speed 1/1000s (to freeze motion, but flash dominates anyway), ISO 200‑400 with heavy grain.", "framing": "vertical 2:3, full‑body shot, subject in the upper center‑left, sky occupying ~60‑65% of the frame, slope and grass ~35‑40%. Strong diagonal composition. Slight tilt (~2‑3°). A small intruding element (a blade of grass or a rabbit ear) in the upper right corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the man and the immediate grass are relatively sharp, rabbits slightly softer, background out of focus and dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid surreal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white on shirt and rabbits)", "harsh shadows with no detail", "dark sky with bright hotspot", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, motion frozen)", "rabbit fur texture with overexposed patches", "chromatic aberration", "barrel distortion", "lens flare", "red‑eye effect on animals" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except faint sky gradient)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features with excessive detail (they should be slightly soft, with harsh flash highlights)", "saturated colors", "vibrant green grass", "bright blue sky", "soft natural lighting" ] }, "negative_prompt": [ "different composition", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic – but here overexposed is desired, so only excessive loss of shape? we keep the man's outline visible)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint sky)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky with details", "detailed background", "HDR look", "saturated green grass", "vibrant colors" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her pose is natural, not overly posed. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised thumb.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a clear, strong thumbs‑up gesture: the fist is tightly closed (all four fingers curled inward), the thumb is extended straight upward, vertical, pointing to the sky. The palm is slightly angled toward the camera (approx. 30‑45°), making the gesture clearly readable. The thumb is well‑defined, no blur.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the raised thumb; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, thumb edge, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, peace sign, OK sign, pointing finger)", "deformed hands", "extra fingers", "missing fingers", "blurred thumb", "thumb not vertical" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "pointing finger", "ok gesture", "peace sign", "blurred hands", "bad anatomy", "twisted fingers", "broken thumb", "unnatural pose", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "iPhone 5 front/back camera aesthetic with harsh on‑camera LED flash, 8MP sensor, grainy texture, moderate compression artifacts, slightly soft details, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited smartphone flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an iPhone 5. The LED flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Skin texture is visible but not overly sharp, with natural pores, fine hairs, and imperfections – typical of 8MP smartphone quality. The composition is slightly tilted, with slight vertical banding noise, a minor lens reflection, and a subtle vignette – all adding authentic iPhone 5 camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow, but with typical smartphone softness. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "iPhone 5 LED FLASH ONLY. The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "harsh flash with high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face. The image has moderate grain and softness typical of 8MP sensor.", "effects": [ "strong, direct LED flash creating hard specular highlights on every sweat droplet and skin texture, but not razor‑sharp", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of iPhone 5 at ISO 400‑800 (heavy grain in shadows, fine grain in highlights, slight chroma noise)", "washed out colors, skin tones pale with a slight blue/green cast from the LED flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding noise visible in the dark sky", "a minor lens reflection (ghosting) in the upper left corner", "subtle vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of iPhone 5 flash. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, iPhone 5 (8MP sensor, f/2.4 lens, LED flash), 33mm equivalent, autofocus with slight softness, shutter speed 1/60s, ISO 400‑800 with visible grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, minor lens reflection.", "focus": "slightly soft, typical of smartphone flash photography, the subject’s face and upper body are relatively sharp but not clinical, background out of focus and very dark.", "visual_fidelity": "grainy, moderate resolution (8MP) aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic iPhone 5 camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens reflection, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs) but not overly sharp", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical sharpness)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR (iPhone 5 had no HDR+ or deep fusion)", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "too much detail", "oversharpened" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone (newer models)", "LED flash (allowed, but only as iPhone 5 LED)", "modern smartphone (iPhone 6 and above)", "daylight", "no flash look", "bright sky", "detailed background", "excessive sharpness", "high megapixel look" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "meta": { "aesthetic_goal": "Ultra Realistic Cinematic Music Cover / Soft Cyberpunk Pastel", "vibe_mode": "Dreamy Rooftop Night / Soft Neon Atmosphere", "image_quality": "Ultra High / Photorealistic Album Cover", "image_type": "Photo", "device_simulation": "Full-frame mirrorless cinematic portrait", "render_settings": { "resolution": "1792x1024", "aspect_ratio": "16:9", "quality_tags": "ultra realistic, pastel cyberpunk, soft glow, cinematic lighting, shallow depth of field, film grain, high dynamic range" } }, "global_context": { "scene_description": "A highly realistic cinematic portrait of a young woman standing on a skyscraper rooftop at night, overlooking a dreamy cyberpunk city filled with soft pastel neon lights (muted cyan, soft pink, lavender, pale amber).", "time_of_day": "Late Night", "weather_atmosphere": "Cool air, gentle wind, thin mist, diffused neon haze, soft atmospheric bloom" }, "artistic_elements": { "mood": "Quiet, emotional, introspective, slightly melancholic but peaceful", "style": "Soft Cyberpunk Realism / Dreamwave", "theme": "Loneliness in a connected world", "narrative": "A solitary figure observing a calm futuristic city glowing softly beneath, representing emotional distance softened by quiet acceptance.", "compositional_technique": "Centered subject with layered depth (foreground softness, mid subject sharp, background blur)", "authenticity_marker": "natural skin texture, subtle wind motion, realistic light falloff, soft RGB split, cinematic imperfections" }, "color_palette": { "dominant_hex_estimates": [ "#0e1117", "#10131c" ], "accent_colors": [ "Soft Cyan", "Pastel Pink", "Lavender Purple", "Muted Amber Highlights" ], "contrast_level": "Medium-Low", "overall_mood": "Dark base with gentle pastel neon glow" }, "composition": { "layout_type": "Music Cover", "camera_angle": "Eye Level", "framing": "Waist Up", "depth_of_field": "Very shallow (creamy bokeh city lights)", "focal_point": "Eyes", "balance": "Centered with subtle asymmetry from city lights", "key_elements": [ "Emotional eyes with soft reflections", "Rooftop edge slightly visible", "Dreamy skyline bokeh", "Soft neon reflections on skin", "Floating typography" ] }, "subject_analysis": { "identity_summary": "Young woman (20-25), calm, introspective, emotionally distant yet peaceful", "visual_signature": { "face_shape": "Soft oval", "eye_details": "Glossy reflective eyes with soft cyan and pink highlights, slight moisture for realism", "skin_complexion": "Highly realistic skin with visible pores, subtle imperfections, soft pastel light reflection", "unique_features": "Micro-expression sadness, relaxed lips, natural asymmetry" }, "hair_logic": { "style": "Loose, slightly messy", "texture": "Soft and natural", "color": "Dark brown / black", "physics": "Gentle wind movement, subtle strand separation, soft rim lighting in pastel tones" }, "pose_and_action": { "description": "Standing calmly near rooftop edge", "facial_expression": "Soft, distant, emotionally reflective", "gaze_direction": "Looking toward city, not directly at camera" } }, "wardrobe": { "top": { "type": "Futuristic techwear jacket", "color": "Matte black", "material": "Soft synthetic fabric with light reflective seams", "style": "Minimalist cyberpunk", "details": "Subtle reflective piping catching pastel neon light, slightly oversized fit", "fit": "Relaxed" } }, "typography": { "title_text": { "content": "PAPERCUT", "position": "Behind subject in sky area", "style": "Grunge Bush-style sans-serif (distressed, eroded edges)", "color": "Soft gradient (Pastel Cyan → Soft Pink)", "texture": "Subtle noise + worn texture overlay", "opacity": "Medium-low", "blend_mode": "Screen", "depth_blur": "Slightly out of focus", "effects": "Light glitch flicker + soft neon bleed" }, "artist_label": { "content": "LINKIN PARK", "position": "Right mid", "style": "Bold uppercase grunge sans-serif", "color": "Soft white with slight texture", "opacity": "Medium", "effects": "Very subtle distortion" }, "secondary_text": { "content": "MoonChill • NIGHT MODE • EDM", "position": "Left mid", "style": "Thin modern sans-serif (clean contrast to grunge)", "color": "Pale cyan", "opacity": "Soft" } }, "environment": { "setting_type": "Skyscraper Rooftop", "location_details": "Minimal rooftop edge visible, expansive futuristic skyline with soft holographic lights", "background_chaos": "Smooth bokeh lights, layered haze, diffused neon glow, no harsh shapes" }, "lighting": { "source": "Diffused pastel neon lights from city below", "fill_light": "Soft frontal glow (cool cyan)", "direction": "Soft upward ambient + gentle side rim lighting", "quality": "Very soft, cinematic, diffused", "shadows": "Soft and natural", "highlights": "Subtle pastel rim light on hair and cheekbones" }, "cinematography": { "optical_physics": { "lens_distortion": "Minimal", "chromatic_aberration": "Very subtle", "bokeh_style": "Creamy circular bokeh" }, "shutter_mechanics": { "motion_blur": "Very minimal" } }, "tech_specs": { "iso": "400", "aperture": "f/1.6", "focal_length": "50mm", "shutter_speed": "1/125s" }, "technical_imperfections": { "focus": "Eyes critically sharp", "sensor_noise": "Fine film grain", "digital_processing": "Soft bloom, pastel grading, slight RGB split, natural skin rendering" }, "final_prompts": { "positive": "ultra realistic cinematic portrait of a young woman on a rooftop at night, soft pastel cyberpunk city lights in cyan pink and lavender, dreamy atmosphere, gentle wind in hair, natural skin texture, shallow depth of field, creamy bokeh, soft neon reflections, emotional expression, music cover aesthetic, grunge style text PAPERCUT, LINKIN PARK, subtle glitch, photorealistic, cinematic lighting", "negative": "anime, cartoon, cgi, overexposed neon, harsh contrast, yellow dominant lighting, plastic skin, unrealistic proportions, watermark" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised hand.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a tight closed fist, with the palm side facing the camera so that the curled fingers and the inner part of the hand are clearly visible. The back of the hand is not dominant. The fingers are fully curled, and the fist looks natural, clean, and confident. The thumb is folded over the other fingers (or placed naturally, not extended). No thumbs‑up, no OK sign, no open palm.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the clenched fist; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, fist edges, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, thumbs up, OK sign, peace sign, pointing, back of hand dominant)", "deformed hands", "extra fingers", "missing fingers", "blurred fist", "flat palm", "knuckles emphasized" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "thumbs up", "ok gesture", "peace sign", "pointing", "back of hand facing camera", "unnatural fist", "broken wrist", "blurred hands", "bad anatomy", "twisted fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "16:9", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at night in a vast windswept grass field, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (distant horizon, sky, faint stars) is heavily darkened but faintly visible. Ultra‑realistic textures of grass, fabric, and soil – all rendered with natural grain and no smoothing. The composition is centered, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, mysterious, unsettling, with a paranormal, liminal space atmosphere.", "scene": { "location": "Vast open moorland or grass field at night. Tall wild grass (height ~40‑80 cm) bending strongly in the wind, creating flowing waves. The ground is uneven, with natural bumps and dips. The horizon is low (upper third of the frame). The sky is dark, with very faint stars barely visible, completely darkened by the flash. The wind is strong and constant, making the grass lean uniformly to one side.", "subject": { "description": "A tall, slender human figure standing motionless in the center of the frame, facing the camera directly (front view). The figure is completely overexposed by the harsh flash – its entire body glows pure white, with no discernible facial features, clothing details, or texture. The silhouette resembles a long, loose robe or mantle that reaches the ground, with a straight, free‑flowing cut. The arms are straight down along the body, hands at thigh level. The figure appears to be unnaturally bright, as if emitting light, but it's actually the flash blowing out all detail. The outline is sharp against the dark background, with a slight halo effect (halation) from the flash.", "pose": "Standing upright, perfectly centered, weight evenly distributed, head straight, arms relaxed at sides." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient night light is visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the figure (pure white, blown out), deep black shadows in the background and under the figure.", "effects": [ "strong, direct flash creating a pure white silhouette of the figure, completely devoid of texture or facial features", "the flash creates a sharp, crisp shadow of the figure on the grass behind it (visible on the ground)", "the grass in the immediate foreground (within 1‑2 meters of the camera) is also overexposed, with bright highlights on individual blades", "background very dark – the horizon line is barely visible as a faint dark band, the sky is pitch black, stars not visible", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass appears pale olive‑green, almost grey; the white figure is pure white; the sky is black", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (figure outline, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The grass loses its warm green, appearing pale and cool. The figure is pure white with a slight blue tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, eye level (camera height approx. 1.5‑1.7 m), centered composition. Full‑body shot (figure from head to feet). Camera distance ~15‑20 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35‑50mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "horizontal 16:9, wide shot, subject centered, slight tilt (~2‑3°), a small intruding element (a blade of grass or a strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the figure and the immediate grass are relatively sharp, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid paranormal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white silhouette)", "harsh shadows with no detail", "pitch black background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, bending in wind, slight motion blur)", "chromatic aberration", "barrel distortion", "lens flare", "halation around the figure" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint horizon)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin (no skin visible)", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "any clothing details on the figure", "bloom (except flash halation)", "soft glow (the figure must be pure white overexposed, not a gentle glow)" ] }, "negative_prompt": [ "different composition", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic) – but here overexposed is desired, so only excessive overexposure that destroys shape? Actually we want blown highlights but the figure's outline must remain clear. So careful: the figure should be pure white but the edges should be visible.", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint horizon)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional motion blur)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background", "HDR look", "saturated colors", "bloom (except flash halation)", "soft glow", "facial recognition" ] }
{ "meta": { "style": "ultra-realistic beach portrait photography", "quality": "8k high resolution", "camera": "Full-frame DSLR", "lens": "85mm f/1.8 portrait lens", "aperture": "f/2.8", "lighting": "natural golden hour sunset light with soft ambient sky glow", "color_grading": "soft cinematic teal and peach tones", "aspect_ratio": "4:5 vertical", "sharpness": "razor sharp focus on subject, slightly softened background" }, "scene": { "location": "sandy beach shoreline", "environment": "gentle ocean waves rolling in behind subject", "time_of_day": "sunset / early dusk", "sky": "pastel blue sky with subtle pink and lavender sunset hues", "atmosphere": "calm, serene, warm coastal breeze", "background_blur": "moderate shallow depth of field with smooth ocean bokeh" }, "subject": { "gender": "female", "age_range": "mid 20s", "physique": "fit, natural proportions, toned yet soft curves", "skin_tone": "light with natural warm undertones", "skin_texture": "natural skin texture with subtle water sheen", "expression": "gentle confident smile, relaxed and approachable", "eyes": "soft expressive eyes looking directly at camera", "hair": { "color": "dark brown", "style": "long, loose, wet, naturally tousled", "detail": "slightly damp strands resting over shoulders and back" } }, "pose": { "stance": "standing upright on wet sand", "left_hand": "resting naturally on top of head, fingers lightly touching hair", "right_hand": "placed on hip creating confident posture", "body_angle": "slightly angled torso toward camera", "gaze_direction": "direct eye contact with camera" }, "wardrobe": { "outfit_type": "minimal two-piece bikini", "top": { "color": "light beige / off-white", "trim": "green edging", "style": "triangle bikini top with thin straps" }, "bottom": { "color": "light beige / off-white", "trim": "green edging", "style": "low-rise bikini bottom" } }, "composition": { "framing": "mid-thigh up portrait", "focus_priority": "sharp focus on face and upper body", "depth_of_field": "shallow depth for subject isolation", "rule_of_thirds": "subject centered with horizon line slightly above mid-frame", "balance": "symmetrical composition with ocean horizon in background" }, "mood": { "vibe": "fresh, natural, confident summer aesthetic", "emotion": "relaxed, empowered, radiant", "energy": "soft coastal elegance" }, "post_processing": { "retouching": "light professional beauty retouch, preserve natural skin texture", "contrast": "moderate contrast for depth", "highlights": "soft glow on skin highlights", "shadows": "balanced soft shadows", "color_enhancement": "enhanced ocean blues and warm sunset
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } } { "subject": { "demographics": "Young adult female, light skin tone with visible tan lines.", "hair": "Platinum blonde hair with distinct dark roots, styled in a messy high bun, loose strands framing the face.", "apparel": "Black strapless bandeau top, minimally visible matching black bottoms.", "accessories": "Large silver hoop earrings, thin silver chain necklace with a star pendant.", "anatomy": "Full, heavy bust with natural gravitational weight due to forward-leaning pose. Visible cleavage and soft tissue volume. Clear tan lines on the upper chest indicating previous sun exposure with a different top.", "skin_details": "Wet, glistening skin texture with visible water droplets. High-resolution pores and skin imperfections. Reflective sheen on shoulders, chest, and face." }, "pose": { "body_position": "Deep squatting/crouching position on the floor. Knees bent deeply outward.", "orientation": "Facing the camera, body leaning forward.", "limbs": "Right arm extended towards the camera (suggesting a selfie angle). Left arm reaching down, hand resting on the floor between the feet.", "head_and_gaze": "Head tilted slightly downward, chin tucked. Eyes looking upward directly into the camera lens with a focused expression." }, "environment": { "setting": "Tiled shower stall or bathroom corner.", "background_elements": "Grey square tiles on walls and floor. Chrome shower mixer/handle visible on the right wall. A white towel hanging on the left side.", "surface_interaction": "Floor tiles appear wet. Water reflections visible on the ground." }, "camera": { "perspective": "High-angle, top-down perspective (selfie style).", "shot_type": "Close-up, full body from a high angle (head to feet visible due to compression).", "focal_length": "Wide-angle lens, creating slight perspective distortion where the head and upper body appear larger than the feet.", "depth_of_field": "Deep depth of field, keeping both the face and the tiled floor in focus." }, "lighting": { "source": "Bright, artificial overhead bathroom lighting.", "quality": "Harsh, direct light creating strong specular highlights on the wet skin (forehead, nose, shoulders, chest).", "shadows": "Deep, sharp shadows cast by the body onto the floor and under the chin/neck area." }, "mood_and_expression": { "emotion": "Candid, intense, slightly provocative but casual.", "facial_expression": "Pouting lips, relaxed facial muscles, piercing upward gaze." }, "style_and_realism": { "aesthetic": "Raw, unfiltered phone photography. Amateur selfie aesthetic.", "fidelity": "Photorealistic, high-fidelity skin texture. No airbrushing or artistic stylization." }, "colors_and_tone": { "palette": "Neutral greys (tiles), skin tones (tan and pale), stark black (clothing), silver (accessories).", "contrast": "High contrast due to bright overhead light and dark shadows.", "saturation": "Natural, slightly muted background with warm skin tones." }, "quality_and_technical_details": { "resolution": "High definition, sharp focus.", "texture_emphasis": "Emphasis on wet skin, hair strands, and tile grout." }, "aspect_ratio_and_output": { "ratio": "3:4", "framing": "Vertical orientation." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve deep squat position", "preserve forward lean angle", "preserve arm extension for selfie perspective", "preserve head tilt and upward gaze" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve high-angle foreshortening", "maintain chest foreground dominance", "prevent flattening of the squat posture" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or artificially supported breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "dry skin", "standing pose" ] } }{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } }{ "subject": { "description": "Young woman with fair skin and long, straight brunette hair parted in the middle. She has almond-shaped hazel-green eyes, a refined nose, and full pink lips with a subtle gloss. She is wearing a tight, blue floral-print halter-neck one-piece swimsuit or bodysuit featuring bright pink flowers and green leaves. The garment has a deep plunging neckline that reveals significant cleavage.", "anatomy_and_proportions": "The subject possesses an extremely voluptuous and heavy bust that is significantly above average in volume. The chest mass is full, projecting forward and outward, heavily affected by gravity due to natural weight. The bust depth is visibly greater than the ribcage depth. The torso is slender, creating a dramatic bust-to-waist ratio. Skin texture is natural with visible pores, faint freckles, and soft tissue volume.", "clothing_fit": "The floral bodysuit fits tightly against the skin, conforming to the heavy curvature of the chest and waist. The fabric is strained slightly by the volume of the bust. Thin halter straps go around the neck." }, "pose": { "stance": "Standing upright with a relaxed posture.", "head_position": "Head is tilted slightly downward, with the chin tucked in, looking up towards the camera through eyelashes.", "limbs": "Arms are extended downwards along the sides of the body, relaxed and out of the primary focal area.", "orientation": "Body is facing forward towards the camera, with a slight, subtle angle." }, "environment": { "location": "A domestic kitchen interior.", "background_elements": "To the left, a wooden countertop with a mosaic tile backsplash in shades of purple, grey, and white. White cabinetry with black knobs. Kitchen utensils (spatulas, spoons) in a holder. To the right, built-in stainless steel and black double wall ovens. Wooden flooring is visible.", "details": "Modern, clean, well-lit residential setting." }, "camera": { "perspective": "High-angle shot, looking down at the subject.", "framing": "Medium shot, capturing the subject from the mid-thighs up to the top of the head.", "focal_length": "35mm to 50mm, creating a sense of intimacy without excessive distortion.", "depth_of_field": "Subject is in sharp focus; the kitchen background is slightly softened but fully distinct.", "shot_type": "Eye-level relative to the high angle, emphasizing the subject's gaze and upper body volume." }, "lighting": { "source": "Soft, diffuse indoor ambient lighting, likely a mix of overhead kitchen fixtures and natural light.", "direction": "Top-down and slightly frontal.", "shadows": "Soft shadows visible in the cleavage and under the chin, defining the volume of the chest and facial features.", "highlights": "Subtle specular highlights on the forehead, nose, and the curvature of the upper chest.", "quality": "Neutral to slightly cool color temperature." }, "mood_and_expression": { "expression": "Neutral to soft, alluring gaze. Direct eye contact with a slight 'doe-eyed' look due to the camera angle.", "atmosphere": "Casual, candid, intimate, domestic.", "emotion": "Calm and confident." }, "style_and_realism": { "aesthetic": "High-fidelity photorealism, resembling a high-quality smartphone photo or candid DSLR shot.", "texture_quality": "Ultra-detailed skin texture, realistic fabric weave, accurate material rendering for the kitchen surfaces (wood, tile, metal).", "render_style": "Unfiltered, raw, authentic photography style." }, "colors_and_tone": { "palette": "Natural skin tones, vibrant blue and pink on the swimsuit, neutral whites, browns, and mosaic purples in the background.", "contrast": "Moderate contrast, preserving shadow detail in the hair and background.", "saturation": "Natural and lifelike, with the swimsuit colors popping against the neutral kitchen tones." }, "quality_and_technical_details": { "resolution": "8k, high definition.", "sharpness": "Crisp focus on the eyes and face.", "noise": "Low ISO, minimal grain." }, "aspect_ratio_and_output": { "ratio": "3:4", "orientation": "Portrait" }, "controlnet": { "pose_control": { "model_type": "OpenPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock head tilt and chin tuck" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve chest foreground dominance", "prevent flat or compressed depth", "maintain clear torso-to-background separation", "ensure high-angle perspective geometry" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or lifted breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "mirror selfies", "phone-in-hand selfies", "reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "more realistic reinterpretation", "naturalization of prominent features", "low angle", "looking away" ] } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a bright emerald green supercar on a countryside road, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (trees, road, the second supercar) is heavily darkened but faintly visible. Ultra‑realistic textures of carbon fiber, car paint, asphalt, and skin (if any visible) – all rendered with natural grain and no smoothing. The composition is strongly tilted (Dutch angle ~25‑35°), with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a aggressive, luxury supercar lifestyle vibe.", "scene": { "location": "Countryside asphalt road, overcast daylight but the flash overpowers everything. Surrounding trees (lush green) are almost black silhouettes. The road has visible cracks and wear. In the distance, another bright emerald green supercar (identical or similar) drives ahead, its shape faintly visible, tail lights reflecting the flash as small red dots.", "car_interior": "Inside a supercar. The door panel is visible on the left, covered in glossy carbon fiber (2x2 twill weave pattern) with strong specular highlights from the flash. The windshield and side window show dark silhouettes of trees. The car's exterior hood (emerald green metallic) is visible in the lower left and middle, with blown highlights and dark reflections.", "protagonist": "A person (Welison style, but face fully covered by a glossy carbon fiber full‑face mask) leaning out of the car window or sitting close to the camera. The mask has a aggressive, futuristic design, with narrow eye slits (dark mesh inside). The mask is highly reflective, showing the flash as bright white hotspots. Only the mask, a small part of the shoulder/neck, and a light gray hoodie or t‑shirt collar are visible. The body is turned slightly toward the camera. The mask occupies the lower right third of the frame (approx. 35‑40% of image). The pose is dominant, mysterious, anonymous.", "second_car": "In the upper central background, another emerald green supercar, slightly blurred by motion and heavily darkened, but its shape recognizable, with headlights or taillights catching the flash." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient overcast daylight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the carbon fiber mask, the car’s green paint, the windshield edges, and any reflective surfaces; deep black shadows in the trees and the second car.", "effects": [ "strong, direct flash creating hard specular highlights on the glossy carbon fiber weave (mask and door panel), on the car’s metallic paint, and on the glass", "the background trees become dark silhouettes with no detail, the road surface shows harsh shadows from the flash", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the emerald green becomes a pale, cool green with blue/cyan cast; carbon fiber appears dark grey with bright reflections", "extremely high contrast – bright white hotspots next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (mask edges, car door lines, windshield frame)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky/trees", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The car’s green loses warmth, looking almost teal; the carbon fiber appears cold.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "First‑person / passenger perspective, strong Dutch angle (tilted ~25‑35° counter‑clockwise), camera very close to the mask (approx. 20‑40 cm). Wide‑angle lens equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, extremely tight composition, mask in lower right, car hood in lower left, second car in upper center. Headroom minimal, dense composition.", "focus": "slightly soft, typical of flash photography, the mask and the immediate car interior are relatively sharp, background and second car out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid supercar snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (strong tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "visible carbon fiber weave texture with glossy reflections", "metallic car paint with blown highlights", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "skin on face or neck (only covered by mask)", "matte plastic mask" ] }, "negative_prompt": [ "different character", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture (except carbon fiber mask)", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky", "detailed background", "HDR look", "saturated greens" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a traditional Spanish restaurant in Valencia, evening, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background details (tables, chairs, bar, other diners) are heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, intimate, capturing a spontaneous moment inside a rustic Spanish eatery.", "scene": { "location": "Traditional Spanish restaurant (restaurante español) in Valencia, evening. The interior features dark wooden tables, red or white tablecloths, rustic chairs, and tiled walls with typical Spanish patterns. In the background, a bar area with bottles and a glowing sign that reads 'RESTAURANTE ESPAÑOL' in warm yellow or red neon (or a carved wooden sign). Other diners are blurred and dark. The floor is ceramic tile. The flash darkens most of the background, leaving only the subject and the sign faintly visible.", "restaurant_details": "Wooden beams on ceiling, hanging jamón serrano, clay plates, wine bottles. The sign 'RESTAURANTE ESPAÑOL' is in a traditional font, perhaps with a small Spanish flag or flamenco motif. It catches the flash with a soft glow.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She sits at a small table, facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands falling over her shoulder. She holds a glass of red wine or sangria in one hand, the other hand resting on the table. A small leather bag hangs on the back of her chair. Her pose is natural, leaning slightly forward, weight on one elbow. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the wine glass." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient warm restaurant light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, glass, and the sign; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the restaurant interior is barely visible as faint silhouettes, the sign 'RESTAURANTE ESPAÑOL' glows softly but is dark overall, other diners are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., wine glass rim, hair strands, sign edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm restaurant tones are completely eliminated, leaving only the raw flash color. The sign's warm color is mostly desaturated but retains a hint of its original hue.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Eye‑level, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos (except the restaurant sign)", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a luxury nightclub VIP booth, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (burgundy quilted walls, black leather furniture) is heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, fabric details, paper money texture, and tattoos – all rendered with natural grain and no smoothing. The composition is a high‑angle shot (top‑down), slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a luxury nightlife, flex culture atmosphere.", "scene": { "location": "Nightclub VIP zone, dark interior, black leather couch with diamond tufting, burgundy soft panel walls with diamond quilting, low ceiling. The floor is covered with scattered US dollar bills. A few glasses and club table in the background, heavily darkened.", "protagonists": { "woman_left": { "position": "Sitting on the left side of the couch, body turned slightly toward camera (~15°), leaning forward. Head lifted, looking upward directly at the camera. Expression: serious, neutral‑dominant, eyes slightly narrowed. Wears a dark fitted top (black) and light grey/white jeans. Metallic strappy sandals. Skin has visible pores and subtle sweat sheen from flash. Hair dark, slightly messy." }, "woman_right": { "position": "Sitting on the right side, body in half‑turn, leaning forward slightly, head raised and turned ~10‑15° toward camera. Expression: playful pout (duck face), lips pursed. Wears a black strapless dress/smooth synthetic fabric. A thin bracelet on wrist, a small tattoo visible on shoulder/collarbone area. Hair dark." } }, "foreground_arm": { "description": "A male arm (tattooed forearm) extending from the lower left corner, holding several thick stacks of US dollar bills (rubber bands visible). The arm creates a diagonal across the frame. The forearm has multiple tattoos, a few bracelets, and a watch. The hand grips the money tightly, fingers showing slight shadows from the flash." }, "money": { "description": "Large amount of US dollar bills scattered on the couch, on the women's laps, and on the floor. The bills are wrinkled, some folded, with visible texture and greenish‑yellow color. The flash creates overexposed highlights on the glossy parts of the notes." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient club light visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on skin (forehead, nose, shoulders), on the money stacks, on the leather couch reflections; deep black shadows in the background and under the women's chins.", "effects": [ "strong, direct flash creating hard specular highlights on the skin, the glossy leather, the metallic sandals, the watch crystal, and the money", "background very dark – the burgundy walls appear almost black, the black leather couch is barely visible except for bright highlights on the tufting", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash, the green of the dollar bills is muted, almost greyish‑green", "extremely high contrast – bright white highlights next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (money edges, women's hair, arm contours)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The dollar bills lose their saturated green, appearing pale olive. Skin tones are pale with a cool undertone.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "High‑angle shot (~50‑70° downward), camera positioned above the subjects, slightly tilted (Dutch angle ~5‑10°). Camera distance to the foreground arm ~25‑35 cm, to the women's faces ~70‑100 cm. Wide‑angle equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "vertical 4:5, medium‑close shot, the two women fill the center and middle, the arm and money in the lower left foreground, the background and floor fill the rest. Headroom minimal, composition dense.", "focus": "slightly soft, typical of flash photography, the foreground arm and money are relatively sharp, the women's faces slightly softer, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid VIP nightclub snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, sweat, fine hairs, freckles)", "visible fabric texture (denim, synthetic top)", "paper money texture (wrinkles, folds, edge roughness)", "tattoo details", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible face of the male arm owner", "excessive cle**", "explicit nudity" ] }, "negative_prompt": [ "different characters", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "HDR look", "saturated colors", "clear faces without shine" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her pose is natural, not overly posed. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised thumb.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a clear, strong thumbs‑up gesture: the fist is tightly closed (all four fingers curled inward), the thumb is extended straight upward, vertical, pointing to the sky. The palm is slightly angled toward the camera (approx. 30‑45°), making the gesture clearly readable. The thumb is well‑defined, no blur.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the raised thumb; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, thumb edge, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, peace sign, OK sign, pointing finger)", "deformed hands", "extra fingers", "missing fingers", "blurred thumb", "thumb not vertical" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "pointing finger", "ok gesture", "peace sign", "blurred hands", "bad anatomy", "twisted fingers", "broken thumb", "unnatural pose", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "16:9", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at night in a vast windswept grass field, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (distant horizon, sky, faint stars) is heavily darkened but faintly visible. Ultra‑realistic textures of grass, fabric, and soil – all rendered with natural grain and no smoothing. The composition is centered, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, mysterious, unsettling, with a paranormal, liminal space atmosphere.", "scene": { "location": "Vast open moorland or grass field at night. Tall wild grass (height ~40‑80 cm) bending strongly in the wind, creating flowing waves. The ground is uneven, with natural bumps and dips. The horizon is low (upper third of the frame). The sky is dark, with very faint stars barely visible, completely darkened by the flash. The wind is strong and constant, making the grass lean uniformly to one side.", "subject": { "description": "A tall, slender human figure standing motionless in the center of the frame, facing the camera directly (front view). The figure is completely overexposed by the harsh flash – its entire body glows pure white, with no discernible facial features, clothing details, or texture. The silhouette resembles a long, loose robe or mantle that reaches the ground, with a straight, free‑flowing cut. The arms are straight down along the body, hands at thigh level. The figure appears to be unnaturally bright, as if emitting light, but it's actually the flash blowing out all detail. The outline is sharp against the dark background, with a slight halo effect (halation) from the flash.", "pose": "Standing upright, perfectly centered, weight evenly distributed, head straight, arms relaxed at sides." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient night light is visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the figure (pure white, blown out), deep black shadows in the background and under the figure.", "effects": [ "strong, direct flash creating a pure white silhouette of the figure, completely devoid of texture or facial features", "the flash creates a sharp, crisp shadow of the figure on the grass behind it (visible on the ground)", "the grass in the immediate foreground (within 1‑2 meters of the camera) is also overexposed, with bright highlights on individual blades", "background very dark – the horizon line is barely visible as a faint dark band, the sky is pitch black, stars not visible", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass appears pale olive‑green, almost grey; the white figure is pure white; the sky is black", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (figure outline, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The grass loses its warm green, appearing pale and cool. The figure is pure white with a slight blue tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, eye level (camera height approx. 1.5‑1.7 m), centered composition. Full‑body shot (figure from head to feet). Camera distance ~15‑20 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35‑50mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "horizontal 16:9, wide shot, subject centered, slight tilt (~2‑3°), a small intruding element (a blade of grass or a strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the figure and the immediate grass are relatively sharp, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid paranormal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white silhouette)", "harsh shadows with no detail", "pitch black background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, bending in wind, slight motion blur)", "chromatic aberration", "barrel distortion", "lens flare", "halation around the figure" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint horizon)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin (no skin visible)", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "any clothing details on the figure", "bloom (except flash halation)", "soft glow (the figure must be pure white overexposed, not a gentle glow)" ] }, "negative_prompt": [ "different composition", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic) – but here overexposed is desired, so only excessive overexposure that destroys shape? Actually we want blown highlights but the figure's outline must remain clear. So careful: the figure should be pure white but the edges should be visible.", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint horizon)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional motion blur)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background", "HDR look", "saturated colors", "bloom (except flash halation)", "soft glow", "facial recognition" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a bright emerald green supercar on a countryside road, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (trees, road, the second supercar) is heavily darkened but faintly visible. Ultra‑realistic textures of carbon fiber, car paint, asphalt, and skin (if any visible) – all rendered with natural grain and no smoothing. The composition is strongly tilted (Dutch angle ~25‑35°), with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a aggressive, luxury supercar lifestyle vibe.", "scene": { "location": "Countryside asphalt road, overcast daylight but the flash overpowers everything. Surrounding trees (lush green) are almost black silhouettes. The road has visible cracks and wear. In the distance, another bright emerald green supercar (identical or similar) drives ahead, its shape faintly visible, tail lights reflecting the flash as small red dots.", "car_interior": "Inside a supercar. The door panel is visible on the left, covered in glossy carbon fiber (2x2 twill weave pattern) with strong specular highlights from the flash. The windshield and side window show dark silhouettes of trees. The car's exterior hood (emerald green metallic) is visible in the lower left and middle, with blown highlights and dark reflections.", "protagonist": "A person (Welison style, but face fully covered by a glossy carbon fiber full‑face mask) leaning out of the car window or sitting close to the camera. The mask has a aggressive, futuristic design, with narrow eye slits (dark mesh inside). The mask is highly reflective, showing the flash as bright white hotspots. Only the mask, a small part of the shoulder/neck, and a light gray hoodie or t‑shirt collar are visible. The body is turned slightly toward the camera. The mask occupies the lower right third of the frame (approx. 35‑40% of image). The pose is dominant, mysterious, anonymous.", "second_car": "In the upper central background, another emerald green supercar, slightly blurred by motion and heavily darkened, but its shape recognizable, with headlights or taillights catching the flash." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient overcast daylight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the carbon fiber mask, the car’s green paint, the windshield edges, and any reflective surfaces; deep black shadows in the trees and the second car.", "effects": [ "strong, direct flash creating hard specular highlights on the glossy carbon fiber weave (mask and door panel), on the car’s metallic paint, and on the glass", "the background trees become dark silhouettes with no detail, the road surface shows harsh shadows from the flash", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the emerald green becomes a pale, cool green with blue/cyan cast; carbon fiber appears dark grey with bright reflections", "extremely high contrast – bright white hotspots next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (mask edges, car door lines, windshield frame)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky/trees", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The car’s green loses warmth, looking almost teal; the carbon fiber appears cold.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "First‑person / passenger perspective, strong Dutch angle (tilted ~25‑35° counter‑clockwise), camera very close to the mask (approx. 20‑40 cm). Wide‑angle lens equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, extremely tight composition, mask in lower right, car hood in lower left, second car in upper center. Headroom minimal, dense composition.", "focus": "slightly soft, typical of flash photography, the mask and the immediate car interior are relatively sharp, background and second car out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid supercar snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (strong tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "visible carbon fiber weave texture with glossy reflections", "metallic car paint with blown highlights", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "skin on face or neck (only covered by mask)", "matte plastic mask" ] }, "negative_prompt": [ "different character", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture (except carbon fiber mask)", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky", "detailed background", "HDR look", "saturated greens" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a luxury nightclub VIP booth, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (burgundy quilted walls, black leather furniture) is heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, fabric details, paper money texture, and tattoos – all rendered with natural grain and no smoothing. The composition is a high‑angle shot (top‑down), slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a luxury nightlife, flex culture atmosphere.", "scene": { "location": "Nightclub VIP zone, dark interior, black leather couch with diamond tufting, burgundy soft panel walls with diamond quilting, low ceiling. The floor is covered with scattered US dollar bills. A few glasses and club table in the background, heavily darkened.", "protagonists": { "woman_left": { "position": "Sitting on the left side of the couch, body turned slightly toward camera (~15°), leaning forward. Head lifted, looking upward directly at the camera. Expression: serious, neutral‑dominant, eyes slightly narrowed. Wears a dark fitted top (black) and light grey/white jeans. Metallic strappy sandals. Skin has visible pores and subtle sweat sheen from flash. Hair dark, slightly messy." }, "woman_right": { "position": "Sitting on the right side, body in half‑turn, leaning forward slightly, head raised and turned ~10‑15° toward camera. Expression: playful pout (duck face), lips pursed. Wears a black strapless dress/smooth synthetic fabric. A thin bracelet on wrist, a small tattoo visible on shoulder/collarbone area. Hair dark." } }, "foreground_arm": { "description": "A male arm (tattooed forearm) extending from the lower left corner, holding several thick stacks of US dollar bills (rubber bands visible). The arm creates a diagonal across the frame. The forearm has multiple tattoos, a few bracelets, and a watch. The hand grips the money tightly, fingers showing slight shadows from the flash." }, "money": { "description": "Large amount of US dollar bills scattered on the couch, on the women's laps, and on the floor. The bills are wrinkled, some folded, with visible texture and greenish‑yellow color. The flash creates overexposed highlights on the glossy parts of the notes." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient club light visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on skin (forehead, nose, shoulders), on the money stacks, on the leather couch reflections; deep black shadows in the background and under the women's chins.", "effects": [ "strong, direct flash creating hard specular highlights on the skin, the glossy leather, the metallic sandals, the watch crystal, and the money", "background very dark – the burgundy walls appear almost black, the black leather couch is barely visible except for bright highlights on the tufting", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash, the green of the dollar bills is muted, almost greyish‑green", "extremely high contrast – bright white highlights next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (money edges, women's hair, arm contours)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The dollar bills lose their saturated green, appearing pale olive. Skin tones are pale with a cool undertone.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "High‑angle shot (~50‑70° downward), camera positioned above the subjects, slightly tilted (Dutch angle ~5‑10°). Camera distance to the foreground arm ~25‑35 cm, to the women's faces ~70‑100 cm. Wide‑angle equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "vertical 4:5, medium‑close shot, the two women fill the center and middle, the arm and money in the lower left foreground, the background and floor fill the rest. Headroom minimal, composition dense.", "focus": "slightly soft, typical of flash photography, the foreground arm and money are relatively sharp, the women's faces slightly softer, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid VIP nightclub snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, sweat, fine hairs, freckles)", "visible fabric texture (denim, synthetic top)", "paper money texture (wrinkles, folds, edge roughness)", "tattoo details", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible face of the male arm owner", "excessive cle**", "explicit nudity" ] }, "negative_prompt": [ "different characters", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "HDR look", "saturated colors", "clear faces without shine" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "2:3", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken outdoors on a grassy hillside in bright midday sunlight, but the flash overpowers the sun, creating deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The sky is heavily darkened but faintly visible, the grass becomes pale greenish‑grey, and the white rabbits appear overexposed with blown highlights. Ultra‑realistic textures of grass, fabric, and rabbit fur – all rendered with natural grain and no smoothing. The composition is dynamic, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, surreal, and whimsical, with a dreamcore, absurdist atmosphere.", "scene": { "location": "A steep grassy hillside on a bright sunny day, but the flash overpowers the sun. The grass is tall (20‑60 cm), vivid green in reality, but appears pale olive‑grey with overexposed patches. Several white rabbits (approximately 4) are scattered across the slope, frozen mid‑action, their white fur blown out with specular highlights. The sky is deep blue originally, but now appears dark grey‑blue with a bright hotspot near the horizon, almost black at the top. A diagonal line runs from the lower left to the upper right, following the slope.", "subject": { "description": "A man in formal clothing, caught mid‑leap, jumping upward and forward along the slope. He is in side profile (facing left), body angled, arms and legs spread dynamically, as if running or dancing in the air. He wears a white short‑sleeve shirt (overexposed, pure white in patches), a black fitted vest (deep charcoal, with bright edges from flash), dark grey trousers (pale grey with harsh shadows), and black dress shoes (dark, reflecting the flash). His face is in profile, expression neutral but slightly intense, eyes visible but with harsh catchlights from the flash. His hair is dark, wind‑blown.", "pose": "Mid‑air, front leg extended downward, back leg horizontal, arms raised and spread with fingers splayed. The body is leaning forward (~10‑15°), head facing direction of motion." }, "animals": { "description": "White rabbits of various sizes, scattered on the grass. Some are sitting, some hopping, their fur overexposed with bright white highlights, shadows underneath them sharp and black. Their eyes reflect the flash with red‑eye effect (typical of 90s compact cameras)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient sunlight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the man's white shirt, the rabbits' fur, and the brightest patches of grass; deep black shadows under the man, under the rabbits, and in the upper sky.", "effects": [ "strong, direct flash creating pure white blown highlights on the white shirt and rabbit fur, with sharp specular reflections", "the sky appears dark grey‑blue, almost black at the top, with a bright circular hotspot near the horizon", "the grass is pale and washed out, with individual blades visible but lacking deep green color", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass is pale olive‑grey, the sky is dark blue‑grey, the black vest appears charcoal, the white shirt is pure white with no detail", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (man's outline, rabbit fur edges, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges", "red‑eye effect on the rabbits (typical of direct flash)" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The green grass becomes pale olive‑grey, the blue sky becomes dark grey‑blue, the white shirt is pure white with a slight cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Low angle (camera below the subject), looking upward at the man, side profile, with the slope rising diagonally from lower left to upper right. Camera distance ~8‑12 m. Wide‑angle lens (~28‑35mm equivalent).", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 28‑35mm equivalent, fixed focus or autofocus with slight softness, aperture f/5.6‑f/8, shutter speed 1/1000s (to freeze motion, but flash dominates anyway), ISO 200‑400 with heavy grain.", "framing": "vertical 2:3, full‑body shot, subject in the upper center‑left, sky occupying ~60‑65% of the frame, slope and grass ~35‑40%. Strong diagonal composition. Slight tilt (~2‑3°). A small intruding element (a blade of grass or a rabbit ear) in the upper right corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the man and the immediate grass are relatively sharp, rabbits slightly softer, background out of focus and dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid surreal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white on shirt and rabbits)", "harsh shadows with no detail", "dark sky with bright hotspot", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, motion frozen)", "rabbit fur texture with overexposed patches", "chromatic aberration", "barrel distortion", "lens flare", "red‑eye effect on animals" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except faint sky gradient)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features with excessive detail (they should be slightly soft, with harsh flash highlights)", "saturated colors", "vibrant green grass", "bright blue sky", "soft natural lighting" ] }, "negative_prompt": [ "different composition", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic – but here overexposed is desired, so only excessive loss of shape? we keep the man's outline visible)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint sky)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky with details", "detailed background", "HDR look", "saturated green grass", "vibrant colors" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "iPhone 5 front/back camera aesthetic with harsh on‑camera LED flash, 8MP sensor, grainy texture, moderate compression artifacts, slightly soft details, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited smartphone flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an iPhone 5. The LED flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Skin texture is visible but not overly sharp, with natural pores, fine hairs, and imperfections – typical of 8MP smartphone quality. The composition is slightly tilted, with slight vertical banding noise, a minor lens reflection, and a subtle vignette – all adding authentic iPhone 5 camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow, but with typical smartphone softness. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "iPhone 5 LED FLASH ONLY. The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "harsh flash with high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face. The image has moderate grain and softness typical of 8MP sensor.", "effects": [ "strong, direct LED flash creating hard specular highlights on every sweat droplet and skin texture, but not razor‑sharp", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of iPhone 5 at ISO 400‑800 (heavy grain in shadows, fine grain in highlights, slight chroma noise)", "washed out colors, skin tones pale with a slight blue/green cast from the LED flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding noise visible in the dark sky", "a minor lens reflection (ghosting) in the upper left corner", "subtle vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of iPhone 5 flash. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, iPhone 5 (8MP sensor, f/2.4 lens, LED flash), 33mm equivalent, autofocus with slight softness, shutter speed 1/60s, ISO 400‑800 with visible grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, minor lens reflection.", "focus": "slightly soft, typical of smartphone flash photography, the subject’s face and upper body are relatively sharp but not clinical, background out of focus and very dark.", "visual_fidelity": "grainy, moderate resolution (8MP) aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic iPhone 5 camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens reflection, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs) but not overly sharp", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical sharpness)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR (iPhone 5 had no HDR+ or deep fusion)", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "too much detail", "oversharpened" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone (newer models)", "LED flash (allowed, but only as iPhone 5 LED)", "modern smartphone (iPhone 6 and above)", "daylight", "no flash look", "bright sky", "detailed background", "excessive sharpness", "high megapixel look" ] }
{ "meta": { "aesthetic_goal": "Ultra Realistic Cinematic Music Cover / Soft Cyberpunk Pastel", "vibe_mode": "Dreamy Rooftop Night / Soft Neon Atmosphere", "image_quality": "Ultra High / Photorealistic Album Cover", "image_type": "Photo", "device_simulation": "Full-frame mirrorless cinematic portrait", "render_settings": { "resolution": "1792x1024", "aspect_ratio": "16:9", "quality_tags": "ultra realistic, pastel cyberpunk, soft glow, cinematic lighting, shallow depth of field, film grain, high dynamic range" } }, "global_context": { "scene_description": "A highly realistic cinematic portrait of a young woman standing on a skyscraper rooftop at night, overlooking a dreamy cyberpunk city filled with soft pastel neon lights (muted cyan, soft pink, lavender, pale amber).", "time_of_day": "Late Night", "weather_atmosphere": "Cool air, gentle wind, thin mist, diffused neon haze, soft atmospheric bloom" }, "artistic_elements": { "mood": "Quiet, emotional, introspective, slightly melancholic but peaceful", "style": "Soft Cyberpunk Realism / Dreamwave", "theme": "Loneliness in a connected world", "narrative": "A solitary figure observing a calm futuristic city glowing softly beneath, representing emotional distance softened by quiet acceptance.", "compositional_technique": "Centered subject with layered depth (foreground softness, mid subject sharp, background blur)", "authenticity_marker": "natural skin texture, subtle wind motion, realistic light falloff, soft RGB split, cinematic imperfections" }, "color_palette": { "dominant_hex_estimates": [ "#0e1117", "#10131c" ], "accent_colors": [ "Soft Cyan", "Pastel Pink", "Lavender Purple", "Muted Amber Highlights" ], "contrast_level": "Medium-Low", "overall_mood": "Dark base with gentle pastel neon glow" }, "composition": { "layout_type": "Music Cover", "camera_angle": "Eye Level", "framing": "Waist Up", "depth_of_field": "Very shallow (creamy bokeh city lights)", "focal_point": "Eyes", "balance": "Centered with subtle asymmetry from city lights", "key_elements": [ "Emotional eyes with soft reflections", "Rooftop edge slightly visible", "Dreamy skyline bokeh", "Soft neon reflections on skin", "Floating typography" ] }, "subject_analysis": { "identity_summary": "Young woman (20-25), calm, introspective, emotionally distant yet peaceful", "visual_signature": { "face_shape": "Soft oval", "eye_details": "Glossy reflective eyes with soft cyan and pink highlights, slight moisture for realism", "skin_complexion": "Highly realistic skin with visible pores, subtle imperfections, soft pastel light reflection", "unique_features": "Micro-expression sadness, relaxed lips, natural asymmetry" }, "hair_logic": { "style": "Loose, slightly messy", "texture": "Soft and natural", "color": "Dark brown / black", "physics": "Gentle wind movement, subtle strand separation, soft rim lighting in pastel tones" }, "pose_and_action": { "description": "Standing calmly near rooftop edge", "facial_expression": "Soft, distant, emotionally reflective", "gaze_direction": "Looking toward city, not directly at camera" } }, "wardrobe": { "top": { "type": "Futuristic techwear jacket", "color": "Matte black", "material": "Soft synthetic fabric with light reflective seams", "style": "Minimalist cyberpunk", "details": "Subtle reflective piping catching pastel neon light, slightly oversized fit", "fit": "Relaxed" } }, "typography": { "title_text": { "content": "PAPERCUT", "position": "Behind subject in sky area", "style": "Grunge Bush-style sans-serif (distressed, eroded edges)", "color": "Soft gradient (Pastel Cyan → Soft Pink)", "texture": "Subtle noise + worn texture overlay", "opacity": "Medium-low", "blend_mode": "Screen", "depth_blur": "Slightly out of focus", "effects": "Light glitch flicker + soft neon bleed" }, "artist_label": { "content": "LINKIN PARK", "position": "Right mid", "style": "Bold uppercase grunge sans-serif", "color": "Soft white with slight texture", "opacity": "Medium", "effects": "Very subtle distortion" }, "secondary_text": { "content": "MoonChill • NIGHT MODE • EDM", "position": "Left mid", "style": "Thin modern sans-serif (clean contrast to grunge)", "color": "Pale cyan", "opacity": "Soft" } }, "environment": { "setting_type": "Skyscraper Rooftop", "location_details": "Minimal rooftop edge visible, expansive futuristic skyline with soft holographic lights", "background_chaos": "Smooth bokeh lights, layered haze, diffused neon glow, no harsh shapes" }, "lighting": { "source": "Diffused pastel neon lights from city below", "fill_light": "Soft frontal glow (cool cyan)", "direction": "Soft upward ambient + gentle side rim lighting", "quality": "Very soft, cinematic, diffused", "shadows": "Soft and natural", "highlights": "Subtle pastel rim light on hair and cheekbones" }, "cinematography": { "optical_physics": { "lens_distortion": "Minimal", "chromatic_aberration": "Very subtle", "bokeh_style": "Creamy circular bokeh" }, "shutter_mechanics": { "motion_blur": "Very minimal" } }, "tech_specs": { "iso": "400", "aperture": "f/1.6", "focal_length": "50mm", "shutter_speed": "1/125s" }, "technical_imperfections": { "focus": "Eyes critically sharp", "sensor_noise": "Fine film grain", "digital_processing": "Soft bloom, pastel grading, slight RGB split, natural skin rendering" }, "final_prompts": { "positive": "ultra realistic cinematic portrait of a young woman on a rooftop at night, soft pastel cyberpunk city lights in cyan pink and lavender, dreamy atmosphere, gentle wind in hair, natural skin texture, shallow depth of field, creamy bokeh, soft neon reflections, emotional expression, music cover aesthetic, grunge style text PAPERCUT, LINKIN PARK, subtle glitch, photorealistic, cinematic lighting", "negative": "anime, cartoon, cgi, overexposed neon, harsh contrast, yellow dominant lighting, plastic skin, unrealistic proportions, watermark" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised hand.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a tight closed fist, with the palm side facing the camera so that the curled fingers and the inner part of the hand are clearly visible. The back of the hand is not dominant. The fingers are fully curled, and the fist looks natural, clean, and confident. The thumb is folded over the other fingers (or placed naturally, not extended). No thumbs‑up, no OK sign, no open palm.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the clenched fist; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, fist edges, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, thumbs up, OK sign, peace sign, pointing, back of hand dominant)", "deformed hands", "extra fingers", "missing fingers", "blurred fist", "flat palm", "knuckles emphasized" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "thumbs up", "ok gesture", "peace sign", "pointing", "back of hand facing camera", "unnatural fist", "broken wrist", "blurred hands", "bad anatomy", "twisted fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "meta": { "style": "ultra-realistic beach portrait photography", "quality": "8k high resolution", "camera": "Full-frame DSLR", "lens": "85mm f/1.8 portrait lens", "aperture": "f/2.8", "lighting": "natural golden hour sunset light with soft ambient sky glow", "color_grading": "soft cinematic teal and peach tones", "aspect_ratio": "4:5 vertical", "sharpness": "razor sharp focus on subject, slightly softened background" }, "scene": { "location": "sandy beach shoreline", "environment": "gentle ocean waves rolling in behind subject", "time_of_day": "sunset / early dusk", "sky": "pastel blue sky with subtle pink and lavender sunset hues", "atmosphere": "calm, serene, warm coastal breeze", "background_blur": "moderate shallow depth of field with smooth ocean bokeh" }, "subject": { "gender": "female", "age_range": "mid 20s", "physique": "fit, natural proportions, toned yet soft curves", "skin_tone": "light with natural warm undertones", "skin_texture": "natural skin texture with subtle water sheen", "expression": "gentle confident smile, relaxed and approachable", "eyes": "soft expressive eyes looking directly at camera", "hair": { "color": "dark brown", "style": "long, loose, wet, naturally tousled", "detail": "slightly damp strands resting over shoulders and back" } }, "pose": { "stance": "standing upright on wet sand", "left_hand": "resting naturally on top of head, fingers lightly touching hair", "right_hand": "placed on hip creating confident posture", "body_angle": "slightly angled torso toward camera", "gaze_direction": "direct eye contact with camera" }, "wardrobe": { "outfit_type": "minimal two-piece bikini", "top": { "color": "light beige / off-white", "trim": "green edging", "style": "triangle bikini top with thin straps" }, "bottom": { "color": "light beige / off-white", "trim": "green edging", "style": "low-rise bikini bottom" } }, "composition": { "framing": "mid-thigh up portrait", "focus_priority": "sharp focus on face and upper body", "depth_of_field": "shallow depth for subject isolation", "rule_of_thirds": "subject centered with horizon line slightly above mid-frame", "balance": "symmetrical composition with ocean horizon in background" }, "mood": { "vibe": "fresh, natural, confident summer aesthetic", "emotion": "relaxed, empowered, radiant", "energy": "soft coastal elegance" }, "post_processing": { "retouching": "light professional beauty retouch, preserve natural skin texture", "contrast": "moderate contrast for depth", "highlights": "soft glow on skin highlights", "shadows": "balanced soft shadows", "color_enhancement": "enhanced ocean blues and warm sunset
{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } } { "subject": { "demographics": "Young adult female, light skin tone with visible tan lines.", "hair": "Platinum blonde hair with distinct dark roots, styled in a messy high bun, loose strands framing the face.", "apparel": "Black strapless bandeau top, minimally visible matching black bottoms.", "accessories": "Large silver hoop earrings, thin silver chain necklace with a star pendant.", "anatomy": "Full, heavy bust with natural gravitational weight due to forward-leaning pose. Visible cleavage and soft tissue volume. Clear tan lines on the upper chest indicating previous sun exposure with a different top.", "skin_details": "Wet, glistening skin texture with visible water droplets. High-resolution pores and skin imperfections. Reflective sheen on shoulders, chest, and face." }, "pose": { "body_position": "Deep squatting/crouching position on the floor. Knees bent deeply outward.", "orientation": "Facing the camera, body leaning forward.", "limbs": "Right arm extended towards the camera (suggesting a selfie angle). Left arm reaching down, hand resting on the floor between the feet.", "head_and_gaze": "Head tilted slightly downward, chin tucked. Eyes looking upward directly into the camera lens with a focused expression." }, "environment": { "setting": "Tiled shower stall or bathroom corner.", "background_elements": "Grey square tiles on walls and floor. Chrome shower mixer/handle visible on the right wall. A white towel hanging on the left side.", "surface_interaction": "Floor tiles appear wet. Water reflections visible on the ground." }, "camera": { "perspective": "High-angle, top-down perspective (selfie style).", "shot_type": "Close-up, full body from a high angle (head to feet visible due to compression).", "focal_length": "Wide-angle lens, creating slight perspective distortion where the head and upper body appear larger than the feet.", "depth_of_field": "Deep depth of field, keeping both the face and the tiled floor in focus." }, "lighting": { "source": "Bright, artificial overhead bathroom lighting.", "quality": "Harsh, direct light creating strong specular highlights on the wet skin (forehead, nose, shoulders, chest).", "shadows": "Deep, sharp shadows cast by the body onto the floor and under the chin/neck area." }, "mood_and_expression": { "emotion": "Candid, intense, slightly provocative but casual.", "facial_expression": "Pouting lips, relaxed facial muscles, piercing upward gaze." }, "style_and_realism": { "aesthetic": "Raw, unfiltered phone photography. Amateur selfie aesthetic.", "fidelity": "Photorealistic, high-fidelity skin texture. No airbrushing or artistic stylization." }, "colors_and_tone": { "palette": "Neutral greys (tiles), skin tones (tan and pale), stark black (clothing), silver (accessories).", "contrast": "High contrast due to bright overhead light and dark shadows.", "saturation": "Natural, slightly muted background with warm skin tones." }, "quality_and_technical_details": { "resolution": "High definition, sharp focus.", "texture_emphasis": "Emphasis on wet skin, hair strands, and tile grout." }, "aspect_ratio_and_output": { "ratio": "3:4", "framing": "Vertical orientation." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve deep squat position", "preserve forward lean angle", "preserve arm extension for selfie perspective", "preserve head tilt and upward gaze" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve high-angle foreshortening", "maintain chest foreground dominance", "prevent flattening of the squat posture" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or artificially supported breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "dry skin", "standing pose" ] } }{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } }{ "subject": { "description": "Young woman with fair skin and long, straight brunette hair parted in the middle. She has almond-shaped hazel-green eyes, a refined nose, and full pink lips with a subtle gloss. She is wearing a tight, blue floral-print halter-neck one-piece swimsuit or bodysuit featuring bright pink flowers and green leaves. The garment has a deep plunging neckline that reveals significant cleavage.", "anatomy_and_proportions": "The subject possesses an extremely voluptuous and heavy bust that is significantly above average in volume. The chest mass is full, projecting forward and outward, heavily affected by gravity due to natural weight. The bust depth is visibly greater than the ribcage depth. The torso is slender, creating a dramatic bust-to-waist ratio. Skin texture is natural with visible pores, faint freckles, and soft tissue volume.", "clothing_fit": "The floral bodysuit fits tightly against the skin, conforming to the heavy curvature of the chest and waist. The fabric is strained slightly by the volume of the bust. Thin halter straps go around the neck." }, "pose": { "stance": "Standing upright with a relaxed posture.", "head_position": "Head is tilted slightly downward, with the chin tucked in, looking up towards the camera through eyelashes.", "limbs": "Arms are extended downwards along the sides of the body, relaxed and out of the primary focal area.", "orientation": "Body is facing forward towards the camera, with a slight, subtle angle." }, "environment": { "location": "A domestic kitchen interior.", "background_elements": "To the left, a wooden countertop with a mosaic tile backsplash in shades of purple, grey, and white. White cabinetry with black knobs. Kitchen utensils (spatulas, spoons) in a holder. To the right, built-in stainless steel and black double wall ovens. Wooden flooring is visible.", "details": "Modern, clean, well-lit residential setting." }, "camera": { "perspective": "High-angle shot, looking down at the subject.", "framing": "Medium shot, capturing the subject from the mid-thighs up to the top of the head.", "focal_length": "35mm to 50mm, creating a sense of intimacy without excessive distortion.", "depth_of_field": "Subject is in sharp focus; the kitchen background is slightly softened but fully distinct.", "shot_type": "Eye-level relative to the high angle, emphasizing the subject's gaze and upper body volume." }, "lighting": { "source": "Soft, diffuse indoor ambient lighting, likely a mix of overhead kitchen fixtures and natural light.", "direction": "Top-down and slightly frontal.", "shadows": "Soft shadows visible in the cleavage and under the chin, defining the volume of the chest and facial features.", "highlights": "Subtle specular highlights on the forehead, nose, and the curvature of the upper chest.", "quality": "Neutral to slightly cool color temperature." }, "mood_and_expression": { "expression": "Neutral to soft, alluring gaze. Direct eye contact with a slight 'doe-eyed' look due to the camera angle.", "atmosphere": "Casual, candid, intimate, domestic.", "emotion": "Calm and confident." }, "style_and_realism": { "aesthetic": "High-fidelity photorealism, resembling a high-quality smartphone photo or candid DSLR shot.", "texture_quality": "Ultra-detailed skin texture, realistic fabric weave, accurate material rendering for the kitchen surfaces (wood, tile, metal).", "render_style": "Unfiltered, raw, authentic photography style." }, "colors_and_tone": { "palette": "Natural skin tones, vibrant blue and pink on the swimsuit, neutral whites, browns, and mosaic purples in the background.", "contrast": "Moderate contrast, preserving shadow detail in the hair and background.", "saturation": "Natural and lifelike, with the swimsuit colors popping against the neutral kitchen tones." }, "quality_and_technical_details": { "resolution": "8k, high definition.", "sharpness": "Crisp focus on the eyes and face.", "noise": "Low ISO, minimal grain." }, "aspect_ratio_and_output": { "ratio": "3:4", "orientation": "Portrait" }, "controlnet": { "pose_control": { "model_type": "OpenPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock head tilt and chin tuck" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve chest foreground dominance", "prevent flat or compressed depth", "maintain clear torso-to-background separation", "ensure high-angle perspective geometry" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or lifted breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "mirror selfies", "phone-in-hand selfies", "reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "more realistic reinterpretation", "naturalization of prominent features", "low angle", "looking away" ] } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a traditional Spanish restaurant in Valencia, evening, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background details (tables, chairs, bar, other diners) are heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, intimate, capturing a spontaneous moment inside a rustic Spanish eatery.", "scene": { "location": "Traditional Spanish restaurant (restaurante español) in Valencia, evening. The interior features dark wooden tables, red or white tablecloths, rustic chairs, and tiled walls with typical Spanish patterns. In the background, a bar area with bottles and a glowing sign that reads 'RESTAURANTE ESPAÑOL' in warm yellow or red neon (or a carved wooden sign). Other diners are blurred and dark. The floor is ceramic tile. The flash darkens most of the background, leaving only the subject and the sign faintly visible.", "restaurant_details": "Wooden beams on ceiling, hanging jamón serrano, clay plates, wine bottles. The sign 'RESTAURANTE ESPAÑOL' is in a traditional font, perhaps with a small Spanish flag or flamenco motif. It catches the flash with a soft glow.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She sits at a small table, facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands falling over her shoulder. She holds a glass of red wine or sangria in one hand, the other hand resting on the table. A small leather bag hangs on the back of her chair. Her pose is natural, leaning slightly forward, weight on one elbow. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the wine glass." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient warm restaurant light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, glass, and the sign; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the restaurant interior is barely visible as faint silhouettes, the sign 'RESTAURANTE ESPAÑOL' glows softly but is dark overall, other diners are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., wine glass rim, hair strands, sign edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm restaurant tones are completely eliminated, leaving only the raw flash color. The sign's warm color is mostly desaturated but retains a hint of its original hue.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Eye‑level, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos (except the restaurant sign)", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her pose is natural, not overly posed. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised thumb.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a clear, strong thumbs‑up gesture: the fist is tightly closed (all four fingers curled inward), the thumb is extended straight upward, vertical, pointing to the sky. The palm is slightly angled toward the camera (approx. 30‑45°), making the gesture clearly readable. The thumb is well‑defined, no blur.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the raised thumb; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, thumb edge, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, peace sign, OK sign, pointing finger)", "deformed hands", "extra fingers", "missing fingers", "blurred thumb", "thumb not vertical" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "pointing finger", "ok gesture", "peace sign", "blurred hands", "bad anatomy", "twisted fingers", "broken thumb", "unnatural pose", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "meta": { "aesthetic_goal": "Ultra Realistic Cinematic Music Cover / Soft Cyberpunk Pastel", "vibe_mode": "Dreamy Rooftop Night / Soft Neon Atmosphere", "image_quality": "Ultra High / Photorealistic Album Cover", "image_type": "Photo", "device_simulation": "Full-frame mirrorless cinematic portrait", "render_settings": { "resolution": "1792x1024", "aspect_ratio": "16:9", "quality_tags": "ultra realistic, pastel cyberpunk, soft glow, cinematic lighting, shallow depth of field, film grain, high dynamic range" } }, "global_context": { "scene_description": "A highly realistic cinematic portrait of a young woman standing on a skyscraper rooftop at night, overlooking a dreamy cyberpunk city filled with soft pastel neon lights (muted cyan, soft pink, lavender, pale amber).", "time_of_day": "Late Night", "weather_atmosphere": "Cool air, gentle wind, thin mist, diffused neon haze, soft atmospheric bloom" }, "artistic_elements": { "mood": "Quiet, emotional, introspective, slightly melancholic but peaceful", "style": "Soft Cyberpunk Realism / Dreamwave", "theme": "Loneliness in a connected world", "narrative": "A solitary figure observing a calm futuristic city glowing softly beneath, representing emotional distance softened by quiet acceptance.", "compositional_technique": "Centered subject with layered depth (foreground softness, mid subject sharp, background blur)", "authenticity_marker": "natural skin texture, subtle wind motion, realistic light falloff, soft RGB split, cinematic imperfections" }, "color_palette": { "dominant_hex_estimates": [ "#0e1117", "#10131c" ], "accent_colors": [ "Soft Cyan", "Pastel Pink", "Lavender Purple", "Muted Amber Highlights" ], "contrast_level": "Medium-Low", "overall_mood": "Dark base with gentle pastel neon glow" }, "composition": { "layout_type": "Music Cover", "camera_angle": "Eye Level", "framing": "Waist Up", "depth_of_field": "Very shallow (creamy bokeh city lights)", "focal_point": "Eyes", "balance": "Centered with subtle asymmetry from city lights", "key_elements": [ "Emotional eyes with soft reflections", "Rooftop edge slightly visible", "Dreamy skyline bokeh", "Soft neon reflections on skin", "Floating typography" ] }, "subject_analysis": { "identity_summary": "Young woman (20-25), calm, introspective, emotionally distant yet peaceful", "visual_signature": { "face_shape": "Soft oval", "eye_details": "Glossy reflective eyes with soft cyan and pink highlights, slight moisture for realism", "skin_complexion": "Highly realistic skin with visible pores, subtle imperfections, soft pastel light reflection", "unique_features": "Micro-expression sadness, relaxed lips, natural asymmetry" }, "hair_logic": { "style": "Loose, slightly messy", "texture": "Soft and natural", "color": "Dark brown / black", "physics": "Gentle wind movement, subtle strand separation, soft rim lighting in pastel tones" }, "pose_and_action": { "description": "Standing calmly near rooftop edge", "facial_expression": "Soft, distant, emotionally reflective", "gaze_direction": "Looking toward city, not directly at camera" } }, "wardrobe": { "top": { "type": "Futuristic techwear jacket", "color": "Matte black", "material": "Soft synthetic fabric with light reflective seams", "style": "Minimalist cyberpunk", "details": "Subtle reflective piping catching pastel neon light, slightly oversized fit", "fit": "Relaxed" } }, "typography": { "title_text": { "content": "PAPERCUT", "position": "Behind subject in sky area", "style": "Grunge Bush-style sans-serif (distressed, eroded edges)", "color": "Soft gradient (Pastel Cyan → Soft Pink)", "texture": "Subtle noise + worn texture overlay", "opacity": "Medium-low", "blend_mode": "Screen", "depth_blur": "Slightly out of focus", "effects": "Light glitch flicker + soft neon bleed" }, "artist_label": { "content": "LINKIN PARK", "position": "Right mid", "style": "Bold uppercase grunge sans-serif", "color": "Soft white with slight texture", "opacity": "Medium", "effects": "Very subtle distortion" }, "secondary_text": { "content": "MoonChill • NIGHT MODE • EDM", "position": "Left mid", "style": "Thin modern sans-serif (clean contrast to grunge)", "color": "Pale cyan", "opacity": "Soft" } }, "environment": { "setting_type": "Skyscraper Rooftop", "location_details": "Minimal rooftop edge visible, expansive futuristic skyline with soft holographic lights", "background_chaos": "Smooth bokeh lights, layered haze, diffused neon glow, no harsh shapes" }, "lighting": { "source": "Diffused pastel neon lights from city below", "fill_light": "Soft frontal glow (cool cyan)", "direction": "Soft upward ambient + gentle side rim lighting", "quality": "Very soft, cinematic, diffused", "shadows": "Soft and natural", "highlights": "Subtle pastel rim light on hair and cheekbones" }, "cinematography": { "optical_physics": { "lens_distortion": "Minimal", "chromatic_aberration": "Very subtle", "bokeh_style": "Creamy circular bokeh" }, "shutter_mechanics": { "motion_blur": "Very minimal" } }, "tech_specs": { "iso": "400", "aperture": "f/1.6", "focal_length": "50mm", "shutter_speed": "1/125s" }, "technical_imperfections": { "focus": "Eyes critically sharp", "sensor_noise": "Fine film grain", "digital_processing": "Soft bloom, pastel grading, slight RGB split, natural skin rendering" }, "final_prompts": { "positive": "ultra realistic cinematic portrait of a young woman on a rooftop at night, soft pastel cyberpunk city lights in cyan pink and lavender, dreamy atmosphere, gentle wind in hair, natural skin texture, shallow depth of field, creamy bokeh, soft neon reflections, emotional expression, music cover aesthetic, grunge style text PAPERCUT, LINKIN PARK, subtle glitch, photorealistic, cinematic lighting", "negative": "anime, cartoon, cgi, overexposed neon, harsh contrast, yellow dominant lighting, plastic skin, unrealistic proportions, watermark" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "16:9", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at night in a vast windswept grass field, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (distant horizon, sky, faint stars) is heavily darkened but faintly visible. Ultra‑realistic textures of grass, fabric, and soil – all rendered with natural grain and no smoothing. The composition is centered, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, mysterious, unsettling, with a paranormal, liminal space atmosphere.", "scene": { "location": "Vast open moorland or grass field at night. Tall wild grass (height ~40‑80 cm) bending strongly in the wind, creating flowing waves. The ground is uneven, with natural bumps and dips. The horizon is low (upper third of the frame). The sky is dark, with very faint stars barely visible, completely darkened by the flash. The wind is strong and constant, making the grass lean uniformly to one side.", "subject": { "description": "A tall, slender human figure standing motionless in the center of the frame, facing the camera directly (front view). The figure is completely overexposed by the harsh flash – its entire body glows pure white, with no discernible facial features, clothing details, or texture. The silhouette resembles a long, loose robe or mantle that reaches the ground, with a straight, free‑flowing cut. The arms are straight down along the body, hands at thigh level. The figure appears to be unnaturally bright, as if emitting light, but it's actually the flash blowing out all detail. The outline is sharp against the dark background, with a slight halo effect (halation) from the flash.", "pose": "Standing upright, perfectly centered, weight evenly distributed, head straight, arms relaxed at sides." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient night light is visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the figure (pure white, blown out), deep black shadows in the background and under the figure.", "effects": [ "strong, direct flash creating a pure white silhouette of the figure, completely devoid of texture or facial features", "the flash creates a sharp, crisp shadow of the figure on the grass behind it (visible on the ground)", "the grass in the immediate foreground (within 1‑2 meters of the camera) is also overexposed, with bright highlights on individual blades", "background very dark – the horizon line is barely visible as a faint dark band, the sky is pitch black, stars not visible", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass appears pale olive‑green, almost grey; the white figure is pure white; the sky is black", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (figure outline, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The grass loses its warm green, appearing pale and cool. The figure is pure white with a slight blue tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, eye level (camera height approx. 1.5‑1.7 m), centered composition. Full‑body shot (figure from head to feet). Camera distance ~15‑20 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35‑50mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "horizontal 16:9, wide shot, subject centered, slight tilt (~2‑3°), a small intruding element (a blade of grass or a strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the figure and the immediate grass are relatively sharp, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid paranormal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white silhouette)", "harsh shadows with no detail", "pitch black background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, bending in wind, slight motion blur)", "chromatic aberration", "barrel distortion", "lens flare", "halation around the figure" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint horizon)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin (no skin visible)", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "any clothing details on the figure", "bloom (except flash halation)", "soft glow (the figure must be pure white overexposed, not a gentle glow)" ] }, "negative_prompt": [ "different composition", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic) – but here overexposed is desired, so only excessive overexposure that destroys shape? Actually we want blown highlights but the figure's outline must remain clear. So careful: the figure should be pure white but the edges should be visible.", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint horizon)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional motion blur)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background", "HDR look", "saturated colors", "bloom (except flash halation)", "soft glow", "facial recognition" ] }
{ "meta": { "style": "ultra-realistic beach portrait photography", "quality": "8k high resolution", "camera": "Full-frame DSLR", "lens": "85mm f/1.8 portrait lens", "aperture": "f/2.8", "lighting": "natural golden hour sunset light with soft ambient sky glow", "color_grading": "soft cinematic teal and peach tones", "aspect_ratio": "4:5 vertical", "sharpness": "razor sharp focus on subject, slightly softened background" }, "scene": { "location": "sandy beach shoreline", "environment": "gentle ocean waves rolling in behind subject", "time_of_day": "sunset / early dusk", "sky": "pastel blue sky with subtle pink and lavender sunset hues", "atmosphere": "calm, serene, warm coastal breeze", "background_blur": "moderate shallow depth of field with smooth ocean bokeh" }, "subject": { "gender": "female", "age_range": "mid 20s", "physique": "fit, natural proportions, toned yet soft curves", "skin_tone": "light with natural warm undertones", "skin_texture": "natural skin texture with subtle water sheen", "expression": "gentle confident smile, relaxed and approachable", "eyes": "soft expressive eyes looking directly at camera", "hair": { "color": "dark brown", "style": "long, loose, wet, naturally tousled", "detail": "slightly damp strands resting over shoulders and back" } }, "pose": { "stance": "standing upright on wet sand", "left_hand": "resting naturally on top of head, fingers lightly touching hair", "right_hand": "placed on hip creating confident posture", "body_angle": "slightly angled torso toward camera", "gaze_direction": "direct eye contact with camera" }, "wardrobe": { "outfit_type": "minimal two-piece bikini", "top": { "color": "light beige / off-white", "trim": "green edging", "style": "triangle bikini top with thin straps" }, "bottom": { "color": "light beige / off-white", "trim": "green edging", "style": "low-rise bikini bottom" } }, "composition": { "framing": "mid-thigh up portrait", "focus_priority": "sharp focus on face and upper body", "depth_of_field": "shallow depth for subject isolation", "rule_of_thirds": "subject centered with horizon line slightly above mid-frame", "balance": "symmetrical composition with ocean horizon in background" }, "mood": { "vibe": "fresh, natural, confident summer aesthetic", "emotion": "relaxed, empowered, radiant", "energy": "soft coastal elegance" }, "post_processing": { "retouching": "light professional beauty retouch, preserve natural skin texture", "contrast": "moderate contrast for depth", "highlights": "soft glow on skin highlights", "shadows": "balanced soft shadows", "color_enhancement": "enhanced ocean blues and warm sunset
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a traditional Spanish restaurant in Valencia, evening, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background details (tables, chairs, bar, other diners) are heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, intimate, capturing a spontaneous moment inside a rustic Spanish eatery.", "scene": { "location": "Traditional Spanish restaurant (restaurante español) in Valencia, evening. The interior features dark wooden tables, red or white tablecloths, rustic chairs, and tiled walls with typical Spanish patterns. In the background, a bar area with bottles and a glowing sign that reads 'RESTAURANTE ESPAÑOL' in warm yellow or red neon (or a carved wooden sign). Other diners are blurred and dark. The floor is ceramic tile. The flash darkens most of the background, leaving only the subject and the sign faintly visible.", "restaurant_details": "Wooden beams on ceiling, hanging jamón serrano, clay plates, wine bottles. The sign 'RESTAURANTE ESPAÑOL' is in a traditional font, perhaps with a small Spanish flag or flamenco motif. It catches the flash with a soft glow.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She sits at a small table, facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands falling over her shoulder. She holds a glass of red wine or sangria in one hand, the other hand resting on the table. A small leather bag hangs on the back of her chair. Her pose is natural, leaning slightly forward, weight on one elbow. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the wine glass." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient warm restaurant light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, glass, and the sign; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the restaurant interior is barely visible as faint silhouettes, the sign 'RESTAURANTE ESPAÑOL' glows softly but is dark overall, other diners are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., wine glass rim, hair strands, sign edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm restaurant tones are completely eliminated, leaving only the raw flash color. The sign's warm color is mostly desaturated but retains a hint of its original hue.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Eye‑level, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos (except the restaurant sign)", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "iPhone 5 front/back camera aesthetic with harsh on‑camera LED flash, 8MP sensor, grainy texture, moderate compression artifacts, slightly soft details, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited smartphone flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an iPhone 5. The LED flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Skin texture is visible but not overly sharp, with natural pores, fine hairs, and imperfections – typical of 8MP smartphone quality. The composition is slightly tilted, with slight vertical banding noise, a minor lens reflection, and a subtle vignette – all adding authentic iPhone 5 camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow, but with typical smartphone softness. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "iPhone 5 LED FLASH ONLY. The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "harsh flash with high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face. The image has moderate grain and softness typical of 8MP sensor.", "effects": [ "strong, direct LED flash creating hard specular highlights on every sweat droplet and skin texture, but not razor‑sharp", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of iPhone 5 at ISO 400‑800 (heavy grain in shadows, fine grain in highlights, slight chroma noise)", "washed out colors, skin tones pale with a slight blue/green cast from the LED flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding noise visible in the dark sky", "a minor lens reflection (ghosting) in the upper left corner", "subtle vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of iPhone 5 flash. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, iPhone 5 (8MP sensor, f/2.4 lens, LED flash), 33mm equivalent, autofocus with slight softness, shutter speed 1/60s, ISO 400‑800 with visible grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, minor lens reflection.", "focus": "slightly soft, typical of smartphone flash photography, the subject’s face and upper body are relatively sharp but not clinical, background out of focus and very dark.", "visual_fidelity": "grainy, moderate resolution (8MP) aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic iPhone 5 camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens reflection, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs) but not overly sharp", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical sharpness)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR (iPhone 5 had no HDR+ or deep fusion)", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "too much detail", "oversharpened" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone (newer models)", "LED flash (allowed, but only as iPhone 5 LED)", "modern smartphone (iPhone 6 and above)", "daylight", "no flash look", "bright sky", "detailed background", "excessive sharpness", "high megapixel look" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised hand.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a tight closed fist, with the palm side facing the camera so that the curled fingers and the inner part of the hand are clearly visible. The back of the hand is not dominant. The fingers are fully curled, and the fist looks natural, clean, and confident. The thumb is folded over the other fingers (or placed naturally, not extended). No thumbs‑up, no OK sign, no open palm.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the clenched fist; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, fist edges, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, thumbs up, OK sign, peace sign, pointing, back of hand dominant)", "deformed hands", "extra fingers", "missing fingers", "blurred fist", "flat palm", "knuckles emphasized" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "thumbs up", "ok gesture", "peace sign", "pointing", "back of hand facing camera", "unnatural fist", "broken wrist", "blurred hands", "bad anatomy", "twisted fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } } { "subject": { "demographics": "Young adult female, light skin tone with visible tan lines.", "hair": "Platinum blonde hair with distinct dark roots, styled in a messy high bun, loose strands framing the face.", "apparel": "Black strapless bandeau top, minimally visible matching black bottoms.", "accessories": "Large silver hoop earrings, thin silver chain necklace with a star pendant.", "anatomy": "Full, heavy bust with natural gravitational weight due to forward-leaning pose. Visible cleavage and soft tissue volume. Clear tan lines on the upper chest indicating previous sun exposure with a different top.", "skin_details": "Wet, glistening skin texture with visible water droplets. High-resolution pores and skin imperfections. Reflective sheen on shoulders, chest, and face." }, "pose": { "body_position": "Deep squatting/crouching position on the floor. Knees bent deeply outward.", "orientation": "Facing the camera, body leaning forward.", "limbs": "Right arm extended towards the camera (suggesting a selfie angle). Left arm reaching down, hand resting on the floor between the feet.", "head_and_gaze": "Head tilted slightly downward, chin tucked. Eyes looking upward directly into the camera lens with a focused expression." }, "environment": { "setting": "Tiled shower stall or bathroom corner.", "background_elements": "Grey square tiles on walls and floor. Chrome shower mixer/handle visible on the right wall. A white towel hanging on the left side.", "surface_interaction": "Floor tiles appear wet. Water reflections visible on the ground." }, "camera": { "perspective": "High-angle, top-down perspective (selfie style).", "shot_type": "Close-up, full body from a high angle (head to feet visible due to compression).", "focal_length": "Wide-angle lens, creating slight perspective distortion where the head and upper body appear larger than the feet.", "depth_of_field": "Deep depth of field, keeping both the face and the tiled floor in focus." }, "lighting": { "source": "Bright, artificial overhead bathroom lighting.", "quality": "Harsh, direct light creating strong specular highlights on the wet skin (forehead, nose, shoulders, chest).", "shadows": "Deep, sharp shadows cast by the body onto the floor and under the chin/neck area." }, "mood_and_expression": { "emotion": "Candid, intense, slightly provocative but casual.", "facial_expression": "Pouting lips, relaxed facial muscles, piercing upward gaze." }, "style_and_realism": { "aesthetic": "Raw, unfiltered phone photography. Amateur selfie aesthetic.", "fidelity": "Photorealistic, high-fidelity skin texture. No airbrushing or artistic stylization." }, "colors_and_tone": { "palette": "Neutral greys (tiles), skin tones (tan and pale), stark black (clothing), silver (accessories).", "contrast": "High contrast due to bright overhead light and dark shadows.", "saturation": "Natural, slightly muted background with warm skin tones." }, "quality_and_technical_details": { "resolution": "High definition, sharp focus.", "texture_emphasis": "Emphasis on wet skin, hair strands, and tile grout." }, "aspect_ratio_and_output": { "ratio": "3:4", "framing": "Vertical orientation." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve deep squat position", "preserve forward lean angle", "preserve arm extension for selfie perspective", "preserve head tilt and upward gaze" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve high-angle foreshortening", "maintain chest foreground dominance", "prevent flattening of the squat posture" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or artificially supported breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "dry skin", "standing pose" ] } }{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } }{ "subject": { "description": "Young woman with fair skin and long, straight brunette hair parted in the middle. She has almond-shaped hazel-green eyes, a refined nose, and full pink lips with a subtle gloss. She is wearing a tight, blue floral-print halter-neck one-piece swimsuit or bodysuit featuring bright pink flowers and green leaves. The garment has a deep plunging neckline that reveals significant cleavage.", "anatomy_and_proportions": "The subject possesses an extremely voluptuous and heavy bust that is significantly above average in volume. The chest mass is full, projecting forward and outward, heavily affected by gravity due to natural weight. The bust depth is visibly greater than the ribcage depth. The torso is slender, creating a dramatic bust-to-waist ratio. Skin texture is natural with visible pores, faint freckles, and soft tissue volume.", "clothing_fit": "The floral bodysuit fits tightly against the skin, conforming to the heavy curvature of the chest and waist. The fabric is strained slightly by the volume of the bust. Thin halter straps go around the neck." }, "pose": { "stance": "Standing upright with a relaxed posture.", "head_position": "Head is tilted slightly downward, with the chin tucked in, looking up towards the camera through eyelashes.", "limbs": "Arms are extended downwards along the sides of the body, relaxed and out of the primary focal area.", "orientation": "Body is facing forward towards the camera, with a slight, subtle angle." }, "environment": { "location": "A domestic kitchen interior.", "background_elements": "To the left, a wooden countertop with a mosaic tile backsplash in shades of purple, grey, and white. White cabinetry with black knobs. Kitchen utensils (spatulas, spoons) in a holder. To the right, built-in stainless steel and black double wall ovens. Wooden flooring is visible.", "details": "Modern, clean, well-lit residential setting." }, "camera": { "perspective": "High-angle shot, looking down at the subject.", "framing": "Medium shot, capturing the subject from the mid-thighs up to the top of the head.", "focal_length": "35mm to 50mm, creating a sense of intimacy without excessive distortion.", "depth_of_field": "Subject is in sharp focus; the kitchen background is slightly softened but fully distinct.", "shot_type": "Eye-level relative to the high angle, emphasizing the subject's gaze and upper body volume." }, "lighting": { "source": "Soft, diffuse indoor ambient lighting, likely a mix of overhead kitchen fixtures and natural light.", "direction": "Top-down and slightly frontal.", "shadows": "Soft shadows visible in the cleavage and under the chin, defining the volume of the chest and facial features.", "highlights": "Subtle specular highlights on the forehead, nose, and the curvature of the upper chest.", "quality": "Neutral to slightly cool color temperature." }, "mood_and_expression": { "expression": "Neutral to soft, alluring gaze. Direct eye contact with a slight 'doe-eyed' look due to the camera angle.", "atmosphere": "Casual, candid, intimate, domestic.", "emotion": "Calm and confident." }, "style_and_realism": { "aesthetic": "High-fidelity photorealism, resembling a high-quality smartphone photo or candid DSLR shot.", "texture_quality": "Ultra-detailed skin texture, realistic fabric weave, accurate material rendering for the kitchen surfaces (wood, tile, metal).", "render_style": "Unfiltered, raw, authentic photography style." }, "colors_and_tone": { "palette": "Natural skin tones, vibrant blue and pink on the swimsuit, neutral whites, browns, and mosaic purples in the background.", "contrast": "Moderate contrast, preserving shadow detail in the hair and background.", "saturation": "Natural and lifelike, with the swimsuit colors popping against the neutral kitchen tones." }, "quality_and_technical_details": { "resolution": "8k, high definition.", "sharpness": "Crisp focus on the eyes and face.", "noise": "Low ISO, minimal grain." }, "aspect_ratio_and_output": { "ratio": "3:4", "orientation": "Portrait" }, "controlnet": { "pose_control": { "model_type": "OpenPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock head tilt and chin tuck" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve chest foreground dominance", "prevent flat or compressed depth", "maintain clear torso-to-background separation", "ensure high-angle perspective geometry" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or lifted breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "mirror selfies", "phone-in-hand selfies", "reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "more realistic reinterpretation", "naturalization of prominent features", "low angle", "looking away" ] } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a luxury nightclub VIP booth, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (burgundy quilted walls, black leather furniture) is heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, fabric details, paper money texture, and tattoos – all rendered with natural grain and no smoothing. The composition is a high‑angle shot (top‑down), slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a luxury nightlife, flex culture atmosphere.", "scene": { "location": "Nightclub VIP zone, dark interior, black leather couch with diamond tufting, burgundy soft panel walls with diamond quilting, low ceiling. The floor is covered with scattered US dollar bills. A few glasses and club table in the background, heavily darkened.", "protagonists": { "woman_left": { "position": "Sitting on the left side of the couch, body turned slightly toward camera (~15°), leaning forward. Head lifted, looking upward directly at the camera. Expression: serious, neutral‑dominant, eyes slightly narrowed. Wears a dark fitted top (black) and light grey/white jeans. Metallic strappy sandals. Skin has visible pores and subtle sweat sheen from flash. Hair dark, slightly messy." }, "woman_right": { "position": "Sitting on the right side, body in half‑turn, leaning forward slightly, head raised and turned ~10‑15° toward camera. Expression: playful pout (duck face), lips pursed. Wears a black strapless dress/smooth synthetic fabric. A thin bracelet on wrist, a small tattoo visible on shoulder/collarbone area. Hair dark." } }, "foreground_arm": { "description": "A male arm (tattooed forearm) extending from the lower left corner, holding several thick stacks of US dollar bills (rubber bands visible). The arm creates a diagonal across the frame. The forearm has multiple tattoos, a few bracelets, and a watch. The hand grips the money tightly, fingers showing slight shadows from the flash." }, "money": { "description": "Large amount of US dollar bills scattered on the couch, on the women's laps, and on the floor. The bills are wrinkled, some folded, with visible texture and greenish‑yellow color. The flash creates overexposed highlights on the glossy parts of the notes." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient club light visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on skin (forehead, nose, shoulders), on the money stacks, on the leather couch reflections; deep black shadows in the background and under the women's chins.", "effects": [ "strong, direct flash creating hard specular highlights on the skin, the glossy leather, the metallic sandals, the watch crystal, and the money", "background very dark – the burgundy walls appear almost black, the black leather couch is barely visible except for bright highlights on the tufting", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash, the green of the dollar bills is muted, almost greyish‑green", "extremely high contrast – bright white highlights next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (money edges, women's hair, arm contours)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The dollar bills lose their saturated green, appearing pale olive. Skin tones are pale with a cool undertone.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "High‑angle shot (~50‑70° downward), camera positioned above the subjects, slightly tilted (Dutch angle ~5‑10°). Camera distance to the foreground arm ~25‑35 cm, to the women's faces ~70‑100 cm. Wide‑angle equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "vertical 4:5, medium‑close shot, the two women fill the center and middle, the arm and money in the lower left foreground, the background and floor fill the rest. Headroom minimal, composition dense.", "focus": "slightly soft, typical of flash photography, the foreground arm and money are relatively sharp, the women's faces slightly softer, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid VIP nightclub snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, sweat, fine hairs, freckles)", "visible fabric texture (denim, synthetic top)", "paper money texture (wrinkles, folds, edge roughness)", "tattoo details", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible face of the male arm owner", "excessive cle**", "explicit nudity" ] }, "negative_prompt": [ "different characters", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "HDR look", "saturated colors", "clear faces without shine" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "2:3", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken outdoors on a grassy hillside in bright midday sunlight, but the flash overpowers the sun, creating deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The sky is heavily darkened but faintly visible, the grass becomes pale greenish‑grey, and the white rabbits appear overexposed with blown highlights. Ultra‑realistic textures of grass, fabric, and rabbit fur – all rendered with natural grain and no smoothing. The composition is dynamic, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, surreal, and whimsical, with a dreamcore, absurdist atmosphere.", "scene": { "location": "A steep grassy hillside on a bright sunny day, but the flash overpowers the sun. The grass is tall (20‑60 cm), vivid green in reality, but appears pale olive‑grey with overexposed patches. Several white rabbits (approximately 4) are scattered across the slope, frozen mid‑action, their white fur blown out with specular highlights. The sky is deep blue originally, but now appears dark grey‑blue with a bright hotspot near the horizon, almost black at the top. A diagonal line runs from the lower left to the upper right, following the slope.", "subject": { "description": "A man in formal clothing, caught mid‑leap, jumping upward and forward along the slope. He is in side profile (facing left), body angled, arms and legs spread dynamically, as if running or dancing in the air. He wears a white short‑sleeve shirt (overexposed, pure white in patches), a black fitted vest (deep charcoal, with bright edges from flash), dark grey trousers (pale grey with harsh shadows), and black dress shoes (dark, reflecting the flash). His face is in profile, expression neutral but slightly intense, eyes visible but with harsh catchlights from the flash. His hair is dark, wind‑blown.", "pose": "Mid‑air, front leg extended downward, back leg horizontal, arms raised and spread with fingers splayed. The body is leaning forward (~10‑15°), head facing direction of motion." }, "animals": { "description": "White rabbits of various sizes, scattered on the grass. Some are sitting, some hopping, their fur overexposed with bright white highlights, shadows underneath them sharp and black. Their eyes reflect the flash with red‑eye effect (typical of 90s compact cameras)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient sunlight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the man's white shirt, the rabbits' fur, and the brightest patches of grass; deep black shadows under the man, under the rabbits, and in the upper sky.", "effects": [ "strong, direct flash creating pure white blown highlights on the white shirt and rabbit fur, with sharp specular reflections", "the sky appears dark grey‑blue, almost black at the top, with a bright circular hotspot near the horizon", "the grass is pale and washed out, with individual blades visible but lacking deep green color", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass is pale olive‑grey, the sky is dark blue‑grey, the black vest appears charcoal, the white shirt is pure white with no detail", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (man's outline, rabbit fur edges, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges", "red‑eye effect on the rabbits (typical of direct flash)" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The green grass becomes pale olive‑grey, the blue sky becomes dark grey‑blue, the white shirt is pure white with a slight cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Low angle (camera below the subject), looking upward at the man, side profile, with the slope rising diagonally from lower left to upper right. Camera distance ~8‑12 m. Wide‑angle lens (~28‑35mm equivalent).", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 28‑35mm equivalent, fixed focus or autofocus with slight softness, aperture f/5.6‑f/8, shutter speed 1/1000s (to freeze motion, but flash dominates anyway), ISO 200‑400 with heavy grain.", "framing": "vertical 2:3, full‑body shot, subject in the upper center‑left, sky occupying ~60‑65% of the frame, slope and grass ~35‑40%. Strong diagonal composition. Slight tilt (~2‑3°). A small intruding element (a blade of grass or a rabbit ear) in the upper right corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the man and the immediate grass are relatively sharp, rabbits slightly softer, background out of focus and dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid surreal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white on shirt and rabbits)", "harsh shadows with no detail", "dark sky with bright hotspot", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, motion frozen)", "rabbit fur texture with overexposed patches", "chromatic aberration", "barrel distortion", "lens flare", "red‑eye effect on animals" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except faint sky gradient)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features with excessive detail (they should be slightly soft, with harsh flash highlights)", "saturated colors", "vibrant green grass", "bright blue sky", "soft natural lighting" ] }, "negative_prompt": [ "different composition", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic – but here overexposed is desired, so only excessive loss of shape? we keep the man's outline visible)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint sky)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky with details", "detailed background", "HDR look", "saturated green grass", "vibrant colors" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a bright emerald green supercar on a countryside road, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (trees, road, the second supercar) is heavily darkened but faintly visible. Ultra‑realistic textures of carbon fiber, car paint, asphalt, and skin (if any visible) – all rendered with natural grain and no smoothing. The composition is strongly tilted (Dutch angle ~25‑35°), with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a aggressive, luxury supercar lifestyle vibe.", "scene": { "location": "Countryside asphalt road, overcast daylight but the flash overpowers everything. Surrounding trees (lush green) are almost black silhouettes. The road has visible cracks and wear. In the distance, another bright emerald green supercar (identical or similar) drives ahead, its shape faintly visible, tail lights reflecting the flash as small red dots.", "car_interior": "Inside a supercar. The door panel is visible on the left, covered in glossy carbon fiber (2x2 twill weave pattern) with strong specular highlights from the flash. The windshield and side window show dark silhouettes of trees. The car's exterior hood (emerald green metallic) is visible in the lower left and middle, with blown highlights and dark reflections.", "protagonist": "A person (Welison style, but face fully covered by a glossy carbon fiber full‑face mask) leaning out of the car window or sitting close to the camera. The mask has a aggressive, futuristic design, with narrow eye slits (dark mesh inside). The mask is highly reflective, showing the flash as bright white hotspots. Only the mask, a small part of the shoulder/neck, and a light gray hoodie or t‑shirt collar are visible. The body is turned slightly toward the camera. The mask occupies the lower right third of the frame (approx. 35‑40% of image). The pose is dominant, mysterious, anonymous.", "second_car": "In the upper central background, another emerald green supercar, slightly blurred by motion and heavily darkened, but its shape recognizable, with headlights or taillights catching the flash." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient overcast daylight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the carbon fiber mask, the car’s green paint, the windshield edges, and any reflective surfaces; deep black shadows in the trees and the second car.", "effects": [ "strong, direct flash creating hard specular highlights on the glossy carbon fiber weave (mask and door panel), on the car’s metallic paint, and on the glass", "the background trees become dark silhouettes with no detail, the road surface shows harsh shadows from the flash", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the emerald green becomes a pale, cool green with blue/cyan cast; carbon fiber appears dark grey with bright reflections", "extremely high contrast – bright white hotspots next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (mask edges, car door lines, windshield frame)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky/trees", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The car’s green loses warmth, looking almost teal; the carbon fiber appears cold.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "First‑person / passenger perspective, strong Dutch angle (tilted ~25‑35° counter‑clockwise), camera very close to the mask (approx. 20‑40 cm). Wide‑angle lens equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, extremely tight composition, mask in lower right, car hood in lower left, second car in upper center. Headroom minimal, dense composition.", "focus": "slightly soft, typical of flash photography, the mask and the immediate car interior are relatively sharp, background and second car out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid supercar snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (strong tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "visible carbon fiber weave texture with glossy reflections", "metallic car paint with blown highlights", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "skin on face or neck (only covered by mask)", "matte plastic mask" ] }, "negative_prompt": [ "different character", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture (except carbon fiber mask)", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky", "detailed background", "HDR look", "saturated greens" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } } { "subject": { "demographics": "Young adult female, light skin tone with visible tan lines.", "hair": "Platinum blonde hair with distinct dark roots, styled in a messy high bun, loose strands framing the face.", "apparel": "Black strapless bandeau top, minimally visible matching black bottoms.", "accessories": "Large silver hoop earrings, thin silver chain necklace with a star pendant.", "anatomy": "Full, heavy bust with natural gravitational weight due to forward-leaning pose. Visible cleavage and soft tissue volume. Clear tan lines on the upper chest indicating previous sun exposure with a different top.", "skin_details": "Wet, glistening skin texture with visible water droplets. High-resolution pores and skin imperfections. Reflective sheen on shoulders, chest, and face." }, "pose": { "body_position": "Deep squatting/crouching position on the floor. Knees bent deeply outward.", "orientation": "Facing the camera, body leaning forward.", "limbs": "Right arm extended towards the camera (suggesting a selfie angle). Left arm reaching down, hand resting on the floor between the feet.", "head_and_gaze": "Head tilted slightly downward, chin tucked. Eyes looking upward directly into the camera lens with a focused expression." }, "environment": { "setting": "Tiled shower stall or bathroom corner.", "background_elements": "Grey square tiles on walls and floor. Chrome shower mixer/handle visible on the right wall. A white towel hanging on the left side.", "surface_interaction": "Floor tiles appear wet. Water reflections visible on the ground." }, "camera": { "perspective": "High-angle, top-down perspective (selfie style).", "shot_type": "Close-up, full body from a high angle (head to feet visible due to compression).", "focal_length": "Wide-angle lens, creating slight perspective distortion where the head and upper body appear larger than the feet.", "depth_of_field": "Deep depth of field, keeping both the face and the tiled floor in focus." }, "lighting": { "source": "Bright, artificial overhead bathroom lighting.", "quality": "Harsh, direct light creating strong specular highlights on the wet skin (forehead, nose, shoulders, chest).", "shadows": "Deep, sharp shadows cast by the body onto the floor and under the chin/neck area." }, "mood_and_expression": { "emotion": "Candid, intense, slightly provocative but casual.", "facial_expression": "Pouting lips, relaxed facial muscles, piercing upward gaze." }, "style_and_realism": { "aesthetic": "Raw, unfiltered phone photography. Amateur selfie aesthetic.", "fidelity": "Photorealistic, high-fidelity skin texture. No airbrushing or artistic stylization." }, "colors_and_tone": { "palette": "Neutral greys (tiles), skin tones (tan and pale), stark black (clothing), silver (accessories).", "contrast": "High contrast due to bright overhead light and dark shadows.", "saturation": "Natural, slightly muted background with warm skin tones." }, "quality_and_technical_details": { "resolution": "High definition, sharp focus.", "texture_emphasis": "Emphasis on wet skin, hair strands, and tile grout." }, "aspect_ratio_and_output": { "ratio": "3:4", "framing": "Vertical orientation." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve deep squat position", "preserve forward lean angle", "preserve arm extension for selfie perspective", "preserve head tilt and upward gaze" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve high-angle foreshortening", "maintain chest foreground dominance", "prevent flattening of the squat posture" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or artificially supported breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "dry skin", "standing pose" ] } }{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } }{ "subject": { "description": "Young woman with fair skin and long, straight brunette hair parted in the middle. She has almond-shaped hazel-green eyes, a refined nose, and full pink lips with a subtle gloss. She is wearing a tight, blue floral-print halter-neck one-piece swimsuit or bodysuit featuring bright pink flowers and green leaves. The garment has a deep plunging neckline that reveals significant cleavage.", "anatomy_and_proportions": "The subject possesses an extremely voluptuous and heavy bust that is significantly above average in volume. The chest mass is full, projecting forward and outward, heavily affected by gravity due to natural weight. The bust depth is visibly greater than the ribcage depth. The torso is slender, creating a dramatic bust-to-waist ratio. Skin texture is natural with visible pores, faint freckles, and soft tissue volume.", "clothing_fit": "The floral bodysuit fits tightly against the skin, conforming to the heavy curvature of the chest and waist. The fabric is strained slightly by the volume of the bust. Thin halter straps go around the neck." }, "pose": { "stance": "Standing upright with a relaxed posture.", "head_position": "Head is tilted slightly downward, with the chin tucked in, looking up towards the camera through eyelashes.", "limbs": "Arms are extended downwards along the sides of the body, relaxed and out of the primary focal area.", "orientation": "Body is facing forward towards the camera, with a slight, subtle angle." }, "environment": { "location": "A domestic kitchen interior.", "background_elements": "To the left, a wooden countertop with a mosaic tile backsplash in shades of purple, grey, and white. White cabinetry with black knobs. Kitchen utensils (spatulas, spoons) in a holder. To the right, built-in stainless steel and black double wall ovens. Wooden flooring is visible.", "details": "Modern, clean, well-lit residential setting." }, "camera": { "perspective": "High-angle shot, looking down at the subject.", "framing": "Medium shot, capturing the subject from the mid-thighs up to the top of the head.", "focal_length": "35mm to 50mm, creating a sense of intimacy without excessive distortion.", "depth_of_field": "Subject is in sharp focus; the kitchen background is slightly softened but fully distinct.", "shot_type": "Eye-level relative to the high angle, emphasizing the subject's gaze and upper body volume." }, "lighting": { "source": "Soft, diffuse indoor ambient lighting, likely a mix of overhead kitchen fixtures and natural light.", "direction": "Top-down and slightly frontal.", "shadows": "Soft shadows visible in the cleavage and under the chin, defining the volume of the chest and facial features.", "highlights": "Subtle specular highlights on the forehead, nose, and the curvature of the upper chest.", "quality": "Neutral to slightly cool color temperature." }, "mood_and_expression": { "expression": "Neutral to soft, alluring gaze. Direct eye contact with a slight 'doe-eyed' look due to the camera angle.", "atmosphere": "Casual, candid, intimate, domestic.", "emotion": "Calm and confident." }, "style_and_realism": { "aesthetic": "High-fidelity photorealism, resembling a high-quality smartphone photo or candid DSLR shot.", "texture_quality": "Ultra-detailed skin texture, realistic fabric weave, accurate material rendering for the kitchen surfaces (wood, tile, metal).", "render_style": "Unfiltered, raw, authentic photography style." }, "colors_and_tone": { "palette": "Natural skin tones, vibrant blue and pink on the swimsuit, neutral whites, browns, and mosaic purples in the background.", "contrast": "Moderate contrast, preserving shadow detail in the hair and background.", "saturation": "Natural and lifelike, with the swimsuit colors popping against the neutral kitchen tones." }, "quality_and_technical_details": { "resolution": "8k, high definition.", "sharpness": "Crisp focus on the eyes and face.", "noise": "Low ISO, minimal grain." }, "aspect_ratio_and_output": { "ratio": "3:4", "orientation": "Portrait" }, "controlnet": { "pose_control": { "model_type": "OpenPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock head tilt and chin tuck" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve chest foreground dominance", "prevent flat or compressed depth", "maintain clear torso-to-background separation", "ensure high-angle perspective geometry" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or lifted breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "mirror selfies", "phone-in-hand selfies", "reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "more realistic reinterpretation", "naturalization of prominent features", "low angle", "looking away" ] } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a luxury nightclub VIP booth, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (burgundy quilted walls, black leather furniture) is heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, fabric details, paper money texture, and tattoos – all rendered with natural grain and no smoothing. The composition is a high‑angle shot (top‑down), slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a luxury nightlife, flex culture atmosphere.", "scene": { "location": "Nightclub VIP zone, dark interior, black leather couch with diamond tufting, burgundy soft panel walls with diamond quilting, low ceiling. The floor is covered with scattered US dollar bills. A few glasses and club table in the background, heavily darkened.", "protagonists": { "woman_left": { "position": "Sitting on the left side of the couch, body turned slightly toward camera (~15°), leaning forward. Head lifted, looking upward directly at the camera. Expression: serious, neutral‑dominant, eyes slightly narrowed. Wears a dark fitted top (black) and light grey/white jeans. Metallic strappy sandals. Skin has visible pores and subtle sweat sheen from flash. Hair dark, slightly messy." }, "woman_right": { "position": "Sitting on the right side, body in half‑turn, leaning forward slightly, head raised and turned ~10‑15° toward camera. Expression: playful pout (duck face), lips pursed. Wears a black strapless dress/smooth synthetic fabric. A thin bracelet on wrist, a small tattoo visible on shoulder/collarbone area. Hair dark." } }, "foreground_arm": { "description": "A male arm (tattooed forearm) extending from the lower left corner, holding several thick stacks of US dollar bills (rubber bands visible). The arm creates a diagonal across the frame. The forearm has multiple tattoos, a few bracelets, and a watch. The hand grips the money tightly, fingers showing slight shadows from the flash." }, "money": { "description": "Large amount of US dollar bills scattered on the couch, on the women's laps, and on the floor. The bills are wrinkled, some folded, with visible texture and greenish‑yellow color. The flash creates overexposed highlights on the glossy parts of the notes." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient club light visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on skin (forehead, nose, shoulders), on the money stacks, on the leather couch reflections; deep black shadows in the background and under the women's chins.", "effects": [ "strong, direct flash creating hard specular highlights on the skin, the glossy leather, the metallic sandals, the watch crystal, and the money", "background very dark – the burgundy walls appear almost black, the black leather couch is barely visible except for bright highlights on the tufting", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash, the green of the dollar bills is muted, almost greyish‑green", "extremely high contrast – bright white highlights next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (money edges, women's hair, arm contours)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The dollar bills lose their saturated green, appearing pale olive. Skin tones are pale with a cool undertone.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "High‑angle shot (~50‑70° downward), camera positioned above the subjects, slightly tilted (Dutch angle ~5‑10°). Camera distance to the foreground arm ~25‑35 cm, to the women's faces ~70‑100 cm. Wide‑angle equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "vertical 4:5, medium‑close shot, the two women fill the center and middle, the arm and money in the lower left foreground, the background and floor fill the rest. Headroom minimal, composition dense.", "focus": "slightly soft, typical of flash photography, the foreground arm and money are relatively sharp, the women's faces slightly softer, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid VIP nightclub snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, sweat, fine hairs, freckles)", "visible fabric texture (denim, synthetic top)", "paper money texture (wrinkles, folds, edge roughness)", "tattoo details", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible face of the male arm owner", "excessive cle**", "explicit nudity" ] }, "negative_prompt": [ "different characters", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "HDR look", "saturated colors", "clear faces without shine" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "2:3", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken outdoors on a grassy hillside in bright midday sunlight, but the flash overpowers the sun, creating deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The sky is heavily darkened but faintly visible, the grass becomes pale greenish‑grey, and the white rabbits appear overexposed with blown highlights. Ultra‑realistic textures of grass, fabric, and rabbit fur – all rendered with natural grain and no smoothing. The composition is dynamic, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, surreal, and whimsical, with a dreamcore, absurdist atmosphere.", "scene": { "location": "A steep grassy hillside on a bright sunny day, but the flash overpowers the sun. The grass is tall (20‑60 cm), vivid green in reality, but appears pale olive‑grey with overexposed patches. Several white rabbits (approximately 4) are scattered across the slope, frozen mid‑action, their white fur blown out with specular highlights. The sky is deep blue originally, but now appears dark grey‑blue with a bright hotspot near the horizon, almost black at the top. A diagonal line runs from the lower left to the upper right, following the slope.", "subject": { "description": "A man in formal clothing, caught mid‑leap, jumping upward and forward along the slope. He is in side profile (facing left), body angled, arms and legs spread dynamically, as if running or dancing in the air. He wears a white short‑sleeve shirt (overexposed, pure white in patches), a black fitted vest (deep charcoal, with bright edges from flash), dark grey trousers (pale grey with harsh shadows), and black dress shoes (dark, reflecting the flash). His face is in profile, expression neutral but slightly intense, eyes visible but with harsh catchlights from the flash. His hair is dark, wind‑blown.", "pose": "Mid‑air, front leg extended downward, back leg horizontal, arms raised and spread with fingers splayed. The body is leaning forward (~10‑15°), head facing direction of motion." }, "animals": { "description": "White rabbits of various sizes, scattered on the grass. Some are sitting, some hopping, their fur overexposed with bright white highlights, shadows underneath them sharp and black. Their eyes reflect the flash with red‑eye effect (typical of 90s compact cameras)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient sunlight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the man's white shirt, the rabbits' fur, and the brightest patches of grass; deep black shadows under the man, under the rabbits, and in the upper sky.", "effects": [ "strong, direct flash creating pure white blown highlights on the white shirt and rabbit fur, with sharp specular reflections", "the sky appears dark grey‑blue, almost black at the top, with a bright circular hotspot near the horizon", "the grass is pale and washed out, with individual blades visible but lacking deep green color", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass is pale olive‑grey, the sky is dark blue‑grey, the black vest appears charcoal, the white shirt is pure white with no detail", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (man's outline, rabbit fur edges, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges", "red‑eye effect on the rabbits (typical of direct flash)" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The green grass becomes pale olive‑grey, the blue sky becomes dark grey‑blue, the white shirt is pure white with a slight cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Low angle (camera below the subject), looking upward at the man, side profile, with the slope rising diagonally from lower left to upper right. Camera distance ~8‑12 m. Wide‑angle lens (~28‑35mm equivalent).", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 28‑35mm equivalent, fixed focus or autofocus with slight softness, aperture f/5.6‑f/8, shutter speed 1/1000s (to freeze motion, but flash dominates anyway), ISO 200‑400 with heavy grain.", "framing": "vertical 2:3, full‑body shot, subject in the upper center‑left, sky occupying ~60‑65% of the frame, slope and grass ~35‑40%. Strong diagonal composition. Slight tilt (~2‑3°). A small intruding element (a blade of grass or a rabbit ear) in the upper right corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the man and the immediate grass are relatively sharp, rabbits slightly softer, background out of focus and dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid surreal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white on shirt and rabbits)", "harsh shadows with no detail", "dark sky with bright hotspot", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, motion frozen)", "rabbit fur texture with overexposed patches", "chromatic aberration", "barrel distortion", "lens flare", "red‑eye effect on animals" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except faint sky gradient)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features with excessive detail (they should be slightly soft, with harsh flash highlights)", "saturated colors", "vibrant green grass", "bright blue sky", "soft natural lighting" ] }, "negative_prompt": [ "different composition", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic – but here overexposed is desired, so only excessive loss of shape? we keep the man's outline visible)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint sky)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky with details", "detailed background", "HDR look", "saturated green grass", "vibrant colors" ] }
{ "meta": { "aesthetic_goal": "Ultra Realistic Cinematic Music Cover / Soft Cyberpunk Pastel", "vibe_mode": "Dreamy Rooftop Night / Soft Neon Atmosphere", "image_quality": "Ultra High / Photorealistic Album Cover", "image_type": "Photo", "device_simulation": "Full-frame mirrorless cinematic portrait", "render_settings": { "resolution": "1792x1024", "aspect_ratio": "16:9", "quality_tags": "ultra realistic, pastel cyberpunk, soft glow, cinematic lighting, shallow depth of field, film grain, high dynamic range" } }, "global_context": { "scene_description": "A highly realistic cinematic portrait of a young woman standing on a skyscraper rooftop at night, overlooking a dreamy cyberpunk city filled with soft pastel neon lights (muted cyan, soft pink, lavender, pale amber).", "time_of_day": "Late Night", "weather_atmosphere": "Cool air, gentle wind, thin mist, diffused neon haze, soft atmospheric bloom" }, "artistic_elements": { "mood": "Quiet, emotional, introspective, slightly melancholic but peaceful", "style": "Soft Cyberpunk Realism / Dreamwave", "theme": "Loneliness in a connected world", "narrative": "A solitary figure observing a calm futuristic city glowing softly beneath, representing emotional distance softened by quiet acceptance.", "compositional_technique": "Centered subject with layered depth (foreground softness, mid subject sharp, background blur)", "authenticity_marker": "natural skin texture, subtle wind motion, realistic light falloff, soft RGB split, cinematic imperfections" }, "color_palette": { "dominant_hex_estimates": [ "#0e1117", "#10131c" ], "accent_colors": [ "Soft Cyan", "Pastel Pink", "Lavender Purple", "Muted Amber Highlights" ], "contrast_level": "Medium-Low", "overall_mood": "Dark base with gentle pastel neon glow" }, "composition": { "layout_type": "Music Cover", "camera_angle": "Eye Level", "framing": "Waist Up", "depth_of_field": "Very shallow (creamy bokeh city lights)", "focal_point": "Eyes", "balance": "Centered with subtle asymmetry from city lights", "key_elements": [ "Emotional eyes with soft reflections", "Rooftop edge slightly visible", "Dreamy skyline bokeh", "Soft neon reflections on skin", "Floating typography" ] }, "subject_analysis": { "identity_summary": "Young woman (20-25), calm, introspective, emotionally distant yet peaceful", "visual_signature": { "face_shape": "Soft oval", "eye_details": "Glossy reflective eyes with soft cyan and pink highlights, slight moisture for realism", "skin_complexion": "Highly realistic skin with visible pores, subtle imperfections, soft pastel light reflection", "unique_features": "Micro-expression sadness, relaxed lips, natural asymmetry" }, "hair_logic": { "style": "Loose, slightly messy", "texture": "Soft and natural", "color": "Dark brown / black", "physics": "Gentle wind movement, subtle strand separation, soft rim lighting in pastel tones" }, "pose_and_action": { "description": "Standing calmly near rooftop edge", "facial_expression": "Soft, distant, emotionally reflective", "gaze_direction": "Looking toward city, not directly at camera" } }, "wardrobe": { "top": { "type": "Futuristic techwear jacket", "color": "Matte black", "material": "Soft synthetic fabric with light reflective seams", "style": "Minimalist cyberpunk", "details": "Subtle reflective piping catching pastel neon light, slightly oversized fit", "fit": "Relaxed" } }, "typography": { "title_text": { "content": "PAPERCUT", "position": "Behind subject in sky area", "style": "Grunge Bush-style sans-serif (distressed, eroded edges)", "color": "Soft gradient (Pastel Cyan → Soft Pink)", "texture": "Subtle noise + worn texture overlay", "opacity": "Medium-low", "blend_mode": "Screen", "depth_blur": "Slightly out of focus", "effects": "Light glitch flicker + soft neon bleed" }, "artist_label": { "content": "LINKIN PARK", "position": "Right mid", "style": "Bold uppercase grunge sans-serif", "color": "Soft white with slight texture", "opacity": "Medium", "effects": "Very subtle distortion" }, "secondary_text": { "content": "MoonChill • NIGHT MODE • EDM", "position": "Left mid", "style": "Thin modern sans-serif (clean contrast to grunge)", "color": "Pale cyan", "opacity": "Soft" } }, "environment": { "setting_type": "Skyscraper Rooftop", "location_details": "Minimal rooftop edge visible, expansive futuristic skyline with soft holographic lights", "background_chaos": "Smooth bokeh lights, layered haze, diffused neon glow, no harsh shapes" }, "lighting": { "source": "Diffused pastel neon lights from city below", "fill_light": "Soft frontal glow (cool cyan)", "direction": "Soft upward ambient + gentle side rim lighting", "quality": "Very soft, cinematic, diffused", "shadows": "Soft and natural", "highlights": "Subtle pastel rim light on hair and cheekbones" }, "cinematography": { "optical_physics": { "lens_distortion": "Minimal", "chromatic_aberration": "Very subtle", "bokeh_style": "Creamy circular bokeh" }, "shutter_mechanics": { "motion_blur": "Very minimal" } }, "tech_specs": { "iso": "400", "aperture": "f/1.6", "focal_length": "50mm", "shutter_speed": "1/125s" }, "technical_imperfections": { "focus": "Eyes critically sharp", "sensor_noise": "Fine film grain", "digital_processing": "Soft bloom, pastel grading, slight RGB split, natural skin rendering" }, "final_prompts": { "positive": "ultra realistic cinematic portrait of a young woman on a rooftop at night, soft pastel cyberpunk city lights in cyan pink and lavender, dreamy atmosphere, gentle wind in hair, natural skin texture, shallow depth of field, creamy bokeh, soft neon reflections, emotional expression, music cover aesthetic, grunge style text PAPERCUT, LINKIN PARK, subtle glitch, photorealistic, cinematic lighting", "negative": "anime, cartoon, cgi, overexposed neon, harsh contrast, yellow dominant lighting, plastic skin, unrealistic proportions, watermark" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "16:9", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at night in a vast windswept grass field, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (distant horizon, sky, faint stars) is heavily darkened but faintly visible. Ultra‑realistic textures of grass, fabric, and soil – all rendered with natural grain and no smoothing. The composition is centered, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, mysterious, unsettling, with a paranormal, liminal space atmosphere.", "scene": { "location": "Vast open moorland or grass field at night. Tall wild grass (height ~40‑80 cm) bending strongly in the wind, creating flowing waves. The ground is uneven, with natural bumps and dips. The horizon is low (upper third of the frame). The sky is dark, with very faint stars barely visible, completely darkened by the flash. The wind is strong and constant, making the grass lean uniformly to one side.", "subject": { "description": "A tall, slender human figure standing motionless in the center of the frame, facing the camera directly (front view). The figure is completely overexposed by the harsh flash – its entire body glows pure white, with no discernible facial features, clothing details, or texture. The silhouette resembles a long, loose robe or mantle that reaches the ground, with a straight, free‑flowing cut. The arms are straight down along the body, hands at thigh level. The figure appears to be unnaturally bright, as if emitting light, but it's actually the flash blowing out all detail. The outline is sharp against the dark background, with a slight halo effect (halation) from the flash.", "pose": "Standing upright, perfectly centered, weight evenly distributed, head straight, arms relaxed at sides." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient night light is visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the figure (pure white, blown out), deep black shadows in the background and under the figure.", "effects": [ "strong, direct flash creating a pure white silhouette of the figure, completely devoid of texture or facial features", "the flash creates a sharp, crisp shadow of the figure on the grass behind it (visible on the ground)", "the grass in the immediate foreground (within 1‑2 meters of the camera) is also overexposed, with bright highlights on individual blades", "background very dark – the horizon line is barely visible as a faint dark band, the sky is pitch black, stars not visible", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass appears pale olive‑green, almost grey; the white figure is pure white; the sky is black", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (figure outline, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The grass loses its warm green, appearing pale and cool. The figure is pure white with a slight blue tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, eye level (camera height approx. 1.5‑1.7 m), centered composition. Full‑body shot (figure from head to feet). Camera distance ~15‑20 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35‑50mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "horizontal 16:9, wide shot, subject centered, slight tilt (~2‑3°), a small intruding element (a blade of grass or a strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the figure and the immediate grass are relatively sharp, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid paranormal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white silhouette)", "harsh shadows with no detail", "pitch black background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, bending in wind, slight motion blur)", "chromatic aberration", "barrel distortion", "lens flare", "halation around the figure" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint horizon)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin (no skin visible)", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "any clothing details on the figure", "bloom (except flash halation)", "soft glow (the figure must be pure white overexposed, not a gentle glow)" ] }, "negative_prompt": [ "different composition", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic) – but here overexposed is desired, so only excessive overexposure that destroys shape? Actually we want blown highlights but the figure's outline must remain clear. So careful: the figure should be pure white but the edges should be visible.", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint horizon)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional motion blur)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background", "HDR look", "saturated colors", "bloom (except flash halation)", "soft glow", "facial recognition" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a traditional Spanish restaurant in Valencia, evening, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background details (tables, chairs, bar, other diners) are heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, intimate, capturing a spontaneous moment inside a rustic Spanish eatery.", "scene": { "location": "Traditional Spanish restaurant (restaurante español) in Valencia, evening. The interior features dark wooden tables, red or white tablecloths, rustic chairs, and tiled walls with typical Spanish patterns. In the background, a bar area with bottles and a glowing sign that reads 'RESTAURANTE ESPAÑOL' in warm yellow or red neon (or a carved wooden sign). Other diners are blurred and dark. The floor is ceramic tile. The flash darkens most of the background, leaving only the subject and the sign faintly visible.", "restaurant_details": "Wooden beams on ceiling, hanging jamón serrano, clay plates, wine bottles. The sign 'RESTAURANTE ESPAÑOL' is in a traditional font, perhaps with a small Spanish flag or flamenco motif. It catches the flash with a soft glow.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She sits at a small table, facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands falling over her shoulder. She holds a glass of red wine or sangria in one hand, the other hand resting on the table. A small leather bag hangs on the back of her chair. Her pose is natural, leaning slightly forward, weight on one elbow. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the wine glass." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient warm restaurant light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, glass, and the sign; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the restaurant interior is barely visible as faint silhouettes, the sign 'RESTAURANTE ESPAÑOL' glows softly but is dark overall, other diners are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., wine glass rim, hair strands, sign edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm restaurant tones are completely eliminated, leaving only the raw flash color. The sign's warm color is mostly desaturated but retains a hint of its original hue.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Eye‑level, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos (except the restaurant sign)", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her pose is natural, not overly posed. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised thumb.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a clear, strong thumbs‑up gesture: the fist is tightly closed (all four fingers curled inward), the thumb is extended straight upward, vertical, pointing to the sky. The palm is slightly angled toward the camera (approx. 30‑45°), making the gesture clearly readable. The thumb is well‑defined, no blur.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the raised thumb; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, thumb edge, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, peace sign, OK sign, pointing finger)", "deformed hands", "extra fingers", "missing fingers", "blurred thumb", "thumb not vertical" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "pointing finger", "ok gesture", "peace sign", "blurred hands", "bad anatomy", "twisted fingers", "broken thumb", "unnatural pose", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised hand.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a tight closed fist, with the palm side facing the camera so that the curled fingers and the inner part of the hand are clearly visible. The back of the hand is not dominant. The fingers are fully curled, and the fist looks natural, clean, and confident. The thumb is folded over the other fingers (or placed naturally, not extended). No thumbs‑up, no OK sign, no open palm.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the clenched fist; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, fist edges, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, thumbs up, OK sign, peace sign, pointing, back of hand dominant)", "deformed hands", "extra fingers", "missing fingers", "blurred fist", "flat palm", "knuckles emphasized" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "thumbs up", "ok gesture", "peace sign", "pointing", "back of hand facing camera", "unnatural fist", "broken wrist", "blurred hands", "bad anatomy", "twisted fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "iPhone 5 front/back camera aesthetic with harsh on‑camera LED flash, 8MP sensor, grainy texture, moderate compression artifacts, slightly soft details, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited smartphone flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an iPhone 5. The LED flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Skin texture is visible but not overly sharp, with natural pores, fine hairs, and imperfections – typical of 8MP smartphone quality. The composition is slightly tilted, with slight vertical banding noise, a minor lens reflection, and a subtle vignette – all adding authentic iPhone 5 camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow, but with typical smartphone softness. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "iPhone 5 LED FLASH ONLY. The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "harsh flash with high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face. The image has moderate grain and softness typical of 8MP sensor.", "effects": [ "strong, direct LED flash creating hard specular highlights on every sweat droplet and skin texture, but not razor‑sharp", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of iPhone 5 at ISO 400‑800 (heavy grain in shadows, fine grain in highlights, slight chroma noise)", "washed out colors, skin tones pale with a slight blue/green cast from the LED flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding noise visible in the dark sky", "a minor lens reflection (ghosting) in the upper left corner", "subtle vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of iPhone 5 flash. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, iPhone 5 (8MP sensor, f/2.4 lens, LED flash), 33mm equivalent, autofocus with slight softness, shutter speed 1/60s, ISO 400‑800 with visible grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, minor lens reflection.", "focus": "slightly soft, typical of smartphone flash photography, the subject’s face and upper body are relatively sharp but not clinical, background out of focus and very dark.", "visual_fidelity": "grainy, moderate resolution (8MP) aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic iPhone 5 camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens reflection, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs) but not overly sharp", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical sharpness)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR (iPhone 5 had no HDR+ or deep fusion)", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "too much detail", "oversharpened" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone (newer models)", "LED flash (allowed, but only as iPhone 5 LED)", "modern smartphone (iPhone 6 and above)", "daylight", "no flash look", "bright sky", "detailed background", "excessive sharpness", "high megapixel look" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
{ "meta": { "style": "ultra-realistic beach portrait photography", "quality": "8k high resolution", "camera": "Full-frame DSLR", "lens": "85mm f/1.8 portrait lens", "aperture": "f/2.8", "lighting": "natural golden hour sunset light with soft ambient sky glow", "color_grading": "soft cinematic teal and peach tones", "aspect_ratio": "4:5 vertical", "sharpness": "razor sharp focus on subject, slightly softened background" }, "scene": { "location": "sandy beach shoreline", "environment": "gentle ocean waves rolling in behind subject", "time_of_day": "sunset / early dusk", "sky": "pastel blue sky with subtle pink and lavender sunset hues", "atmosphere": "calm, serene, warm coastal breeze", "background_blur": "moderate shallow depth of field with smooth ocean bokeh" }, "subject": { "gender": "female", "age_range": "mid 20s", "physique": "fit, natural proportions, toned yet soft curves", "skin_tone": "light with natural warm undertones", "skin_texture": "natural skin texture with subtle water sheen", "expression": "gentle confident smile, relaxed and approachable", "eyes": "soft expressive eyes looking directly at camera", "hair": { "color": "dark brown", "style": "long, loose, wet, naturally tousled", "detail": "slightly damp strands resting over shoulders and back" } }, "pose": { "stance": "standing upright on wet sand", "left_hand": "resting naturally on top of head, fingers lightly touching hair", "right_hand": "placed on hip creating confident posture", "body_angle": "slightly angled torso toward camera", "gaze_direction": "direct eye contact with camera" }, "wardrobe": { "outfit_type": "minimal two-piece bikini", "top": { "color": "light beige / off-white", "trim": "green edging", "style": "triangle bikini top with thin straps" }, "bottom": { "color": "light beige / off-white", "trim": "green edging", "style": "low-rise bikini bottom" } }, "composition": { "framing": "mid-thigh up portrait", "focus_priority": "sharp focus on face and upper body", "depth_of_field": "shallow depth for subject isolation", "rule_of_thirds": "subject centered with horizon line slightly above mid-frame", "balance": "symmetrical composition with ocean horizon in background" }, "mood": { "vibe": "fresh, natural, confident summer aesthetic", "emotion": "relaxed, empowered, radiant", "energy": "soft coastal elegance" }, "post_processing": { "retouching": "light professional beauty retouch, preserve natural skin texture", "contrast": "moderate contrast for depth", "highlights": "soft glow on skin highlights", "shadows": "balanced soft shadows", "color_enhancement": "enhanced ocean blues and warm sunset
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a bright emerald green supercar on a countryside road, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (trees, road, the second supercar) is heavily darkened but faintly visible. Ultra‑realistic textures of carbon fiber, car paint, asphalt, and skin (if any visible) – all rendered with natural grain and no smoothing. The composition is strongly tilted (Dutch angle ~25‑35°), with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a aggressive, luxury supercar lifestyle vibe.", "scene": { "location": "Countryside asphalt road, overcast daylight but the flash overpowers everything. Surrounding trees (lush green) are almost black silhouettes. The road has visible cracks and wear. In the distance, another bright emerald green supercar (identical or similar) drives ahead, its shape faintly visible, tail lights reflecting the flash as small red dots.", "car_interior": "Inside a supercar. The door panel is visible on the left, covered in glossy carbon fiber (2x2 twill weave pattern) with strong specular highlights from the flash. The windshield and side window show dark silhouettes of trees. The car's exterior hood (emerald green metallic) is visible in the lower left and middle, with blown highlights and dark reflections.", "protagonist": "A person (Welison style, but face fully covered by a glossy carbon fiber full‑face mask) leaning out of the car window or sitting close to the camera. The mask has a aggressive, futuristic design, with narrow eye slits (dark mesh inside). The mask is highly reflective, showing the flash as bright white hotspots. Only the mask, a small part of the shoulder/neck, and a light gray hoodie or t‑shirt collar are visible. The body is turned slightly toward the camera. The mask occupies the lower right third of the frame (approx. 35‑40% of image). The pose is dominant, mysterious, anonymous.", "second_car": "In the upper central background, another emerald green supercar, slightly blurred by motion and heavily darkened, but its shape recognizable, with headlights or taillights catching the flash." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient overcast daylight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the carbon fiber mask, the car’s green paint, the windshield edges, and any reflective surfaces; deep black shadows in the trees and the second car.", "effects": [ "strong, direct flash creating hard specular highlights on the glossy carbon fiber weave (mask and door panel), on the car’s metallic paint, and on the glass", "the background trees become dark silhouettes with no detail, the road surface shows harsh shadows from the flash", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the emerald green becomes a pale, cool green with blue/cyan cast; carbon fiber appears dark grey with bright reflections", "extremely high contrast – bright white hotspots next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (mask edges, car door lines, windshield frame)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky/trees", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The car’s green loses warmth, looking almost teal; the carbon fiber appears cold.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "First‑person / passenger perspective, strong Dutch angle (tilted ~25‑35° counter‑clockwise), camera very close to the mask (approx. 20‑40 cm). Wide‑angle lens equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, extremely tight composition, mask in lower right, car hood in lower left, second car in upper center. Headroom minimal, dense composition.", "focus": "slightly soft, typical of flash photography, the mask and the immediate car interior are relatively sharp, background and second car out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid supercar snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (strong tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "visible carbon fiber weave texture with glossy reflections", "metallic car paint with blown highlights", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "skin on face or neck (only covered by mask)", "matte plastic mask" ] }, "negative_prompt": [ "different character", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture (except carbon fiber mask)", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky", "detailed background", "HDR look", "saturated greens" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "2:3", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken outdoors on a grassy hillside in bright midday sunlight, but the flash overpowers the sun, creating deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The sky is heavily darkened but faintly visible, the grass becomes pale greenish‑grey, and the white rabbits appear overexposed with blown highlights. Ultra‑realistic textures of grass, fabric, and rabbit fur – all rendered with natural grain and no smoothing. The composition is dynamic, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, surreal, and whimsical, with a dreamcore, absurdist atmosphere.", "scene": { "location": "A steep grassy hillside on a bright sunny day, but the flash overpowers the sun. The grass is tall (20‑60 cm), vivid green in reality, but appears pale olive‑grey with overexposed patches. Several white rabbits (approximately 4) are scattered across the slope, frozen mid‑action, their white fur blown out with specular highlights. The sky is deep blue originally, but now appears dark grey‑blue with a bright hotspot near the horizon, almost black at the top. A diagonal line runs from the lower left to the upper right, following the slope.", "subject": { "description": "A man in formal clothing, caught mid‑leap, jumping upward and forward along the slope. He is in side profile (facing left), body angled, arms and legs spread dynamically, as if running or dancing in the air. He wears a white short‑sleeve shirt (overexposed, pure white in patches), a black fitted vest (deep charcoal, with bright edges from flash), dark grey trousers (pale grey with harsh shadows), and black dress shoes (dark, reflecting the flash). His face is in profile, expression neutral but slightly intense, eyes visible but with harsh catchlights from the flash. His hair is dark, wind‑blown.", "pose": "Mid‑air, front leg extended downward, back leg horizontal, arms raised and spread with fingers splayed. The body is leaning forward (~10‑15°), head facing direction of motion." }, "animals": { "description": "White rabbits of various sizes, scattered on the grass. Some are sitting, some hopping, their fur overexposed with bright white highlights, shadows underneath them sharp and black. Their eyes reflect the flash with red‑eye effect (typical of 90s compact cameras)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient sunlight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the man's white shirt, the rabbits' fur, and the brightest patches of grass; deep black shadows under the man, under the rabbits, and in the upper sky.", "effects": [ "strong, direct flash creating pure white blown highlights on the white shirt and rabbit fur, with sharp specular reflections", "the sky appears dark grey‑blue, almost black at the top, with a bright circular hotspot near the horizon", "the grass is pale and washed out, with individual blades visible but lacking deep green color", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass is pale olive‑grey, the sky is dark blue‑grey, the black vest appears charcoal, the white shirt is pure white with no detail", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (man's outline, rabbit fur edges, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges", "red‑eye effect on the rabbits (typical of direct flash)" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The green grass becomes pale olive‑grey, the blue sky becomes dark grey‑blue, the white shirt is pure white with a slight cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Low angle (camera below the subject), looking upward at the man, side profile, with the slope rising diagonally from lower left to upper right. Camera distance ~8‑12 m. Wide‑angle lens (~28‑35mm equivalent).", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 28‑35mm equivalent, fixed focus or autofocus with slight softness, aperture f/5.6‑f/8, shutter speed 1/1000s (to freeze motion, but flash dominates anyway), ISO 200‑400 with heavy grain.", "framing": "vertical 2:3, full‑body shot, subject in the upper center‑left, sky occupying ~60‑65% of the frame, slope and grass ~35‑40%. Strong diagonal composition. Slight tilt (~2‑3°). A small intruding element (a blade of grass or a rabbit ear) in the upper right corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the man and the immediate grass are relatively sharp, rabbits slightly softer, background out of focus and dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid surreal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white on shirt and rabbits)", "harsh shadows with no detail", "dark sky with bright hotspot", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, motion frozen)", "rabbit fur texture with overexposed patches", "chromatic aberration", "barrel distortion", "lens flare", "red‑eye effect on animals" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except faint sky gradient)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features with excessive detail (they should be slightly soft, with harsh flash highlights)", "saturated colors", "vibrant green grass", "bright blue sky", "soft natural lighting" ] }, "negative_prompt": [ "different composition", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic – but here overexposed is desired, so only excessive loss of shape? we keep the man's outline visible)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint sky)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky with details", "detailed background", "HDR look", "saturated green grass", "vibrant colors" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a bright emerald green supercar on a countryside road, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (trees, road, the second supercar) is heavily darkened but faintly visible. Ultra‑realistic textures of carbon fiber, car paint, asphalt, and skin (if any visible) – all rendered with natural grain and no smoothing. The composition is strongly tilted (Dutch angle ~25‑35°), with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a aggressive, luxury supercar lifestyle vibe.", "scene": { "location": "Countryside asphalt road, overcast daylight but the flash overpowers everything. Surrounding trees (lush green) are almost black silhouettes. The road has visible cracks and wear. In the distance, another bright emerald green supercar (identical or similar) drives ahead, its shape faintly visible, tail lights reflecting the flash as small red dots.", "car_interior": "Inside a supercar. The door panel is visible on the left, covered in glossy carbon fiber (2x2 twill weave pattern) with strong specular highlights from the flash. The windshield and side window show dark silhouettes of trees. The car's exterior hood (emerald green metallic) is visible in the lower left and middle, with blown highlights and dark reflections.", "protagonist": "A person (Welison style, but face fully covered by a glossy carbon fiber full‑face mask) leaning out of the car window or sitting close to the camera. The mask has a aggressive, futuristic design, with narrow eye slits (dark mesh inside). The mask is highly reflective, showing the flash as bright white hotspots. Only the mask, a small part of the shoulder/neck, and a light gray hoodie or t‑shirt collar are visible. The body is turned slightly toward the camera. The mask occupies the lower right third of the frame (approx. 35‑40% of image). The pose is dominant, mysterious, anonymous.", "second_car": "In the upper central background, another emerald green supercar, slightly blurred by motion and heavily darkened, but its shape recognizable, with headlights or taillights catching the flash." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient overcast daylight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the carbon fiber mask, the car’s green paint, the windshield edges, and any reflective surfaces; deep black shadows in the trees and the second car.", "effects": [ "strong, direct flash creating hard specular highlights on the glossy carbon fiber weave (mask and door panel), on the car’s metallic paint, and on the glass", "the background trees become dark silhouettes with no detail, the road surface shows harsh shadows from the flash", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the emerald green becomes a pale, cool green with blue/cyan cast; carbon fiber appears dark grey with bright reflections", "extremely high contrast – bright white hotspots next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (mask edges, car door lines, windshield frame)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky/trees", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The car’s green loses warmth, looking almost teal; the carbon fiber appears cold.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "First‑person / passenger perspective, strong Dutch angle (tilted ~25‑35° counter‑clockwise), camera very close to the mask (approx. 20‑40 cm). Wide‑angle lens equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, extremely tight composition, mask in lower right, car hood in lower left, second car in upper center. Headroom minimal, dense composition.", "focus": "slightly soft, typical of flash photography, the mask and the immediate car interior are relatively sharp, background and second car out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid supercar snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (strong tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "visible carbon fiber weave texture with glossy reflections", "metallic car paint with blown highlights", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "skin on face or neck (only covered by mask)", "matte plastic mask" ] }, "negative_prompt": [ "different character", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture (except carbon fiber mask)", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky", "detailed background", "HDR look", "saturated greens" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "iPhone 5 front/back camera aesthetic with harsh on‑camera LED flash, 8MP sensor, grainy texture, moderate compression artifacts, slightly soft details, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited smartphone flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an iPhone 5. The LED flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Skin texture is visible but not overly sharp, with natural pores, fine hairs, and imperfections – typical of 8MP smartphone quality. The composition is slightly tilted, with slight vertical banding noise, a minor lens reflection, and a subtle vignette – all adding authentic iPhone 5 camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow, but with typical smartphone softness. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "iPhone 5 LED FLASH ONLY. The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "harsh flash with high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face. The image has moderate grain and softness typical of 8MP sensor.", "effects": [ "strong, direct LED flash creating hard specular highlights on every sweat droplet and skin texture, but not razor‑sharp", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of iPhone 5 at ISO 400‑800 (heavy grain in shadows, fine grain in highlights, slight chroma noise)", "washed out colors, skin tones pale with a slight blue/green cast from the LED flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding noise visible in the dark sky", "a minor lens reflection (ghosting) in the upper left corner", "subtle vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of iPhone 5 flash. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, iPhone 5 (8MP sensor, f/2.4 lens, LED flash), 33mm equivalent, autofocus with slight softness, shutter speed 1/60s, ISO 400‑800 with visible grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, minor lens reflection.", "focus": "slightly soft, typical of smartphone flash photography, the subject’s face and upper body are relatively sharp but not clinical, background out of focus and very dark.", "visual_fidelity": "grainy, moderate resolution (8MP) aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic iPhone 5 camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens reflection, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs) but not overly sharp", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical sharpness)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR (iPhone 5 had no HDR+ or deep fusion)", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "too much detail", "oversharpened" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone (newer models)", "LED flash (allowed, but only as iPhone 5 LED)", "modern smartphone (iPhone 6 and above)", "daylight", "no flash look", "bright sky", "detailed background", "excessive sharpness", "high megapixel look" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "meta": { "aesthetic_goal": "Ultra Realistic Cinematic Music Cover / Soft Cyberpunk Pastel", "vibe_mode": "Dreamy Rooftop Night / Soft Neon Atmosphere", "image_quality": "Ultra High / Photorealistic Album Cover", "image_type": "Photo", "device_simulation": "Full-frame mirrorless cinematic portrait", "render_settings": { "resolution": "1792x1024", "aspect_ratio": "16:9", "quality_tags": "ultra realistic, pastel cyberpunk, soft glow, cinematic lighting, shallow depth of field, film grain, high dynamic range" } }, "global_context": { "scene_description": "A highly realistic cinematic portrait of a young woman standing on a skyscraper rooftop at night, overlooking a dreamy cyberpunk city filled with soft pastel neon lights (muted cyan, soft pink, lavender, pale amber).", "time_of_day": "Late Night", "weather_atmosphere": "Cool air, gentle wind, thin mist, diffused neon haze, soft atmospheric bloom" }, "artistic_elements": { "mood": "Quiet, emotional, introspective, slightly melancholic but peaceful", "style": "Soft Cyberpunk Realism / Dreamwave", "theme": "Loneliness in a connected world", "narrative": "A solitary figure observing a calm futuristic city glowing softly beneath, representing emotional distance softened by quiet acceptance.", "compositional_technique": "Centered subject with layered depth (foreground softness, mid subject sharp, background blur)", "authenticity_marker": "natural skin texture, subtle wind motion, realistic light falloff, soft RGB split, cinematic imperfections" }, "color_palette": { "dominant_hex_estimates": [ "#0e1117", "#10131c" ], "accent_colors": [ "Soft Cyan", "Pastel Pink", "Lavender Purple", "Muted Amber Highlights" ], "contrast_level": "Medium-Low", "overall_mood": "Dark base with gentle pastel neon glow" }, "composition": { "layout_type": "Music Cover", "camera_angle": "Eye Level", "framing": "Waist Up", "depth_of_field": "Very shallow (creamy bokeh city lights)", "focal_point": "Eyes", "balance": "Centered with subtle asymmetry from city lights", "key_elements": [ "Emotional eyes with soft reflections", "Rooftop edge slightly visible", "Dreamy skyline bokeh", "Soft neon reflections on skin", "Floating typography" ] }, "subject_analysis": { "identity_summary": "Young woman (20-25), calm, introspective, emotionally distant yet peaceful", "visual_signature": { "face_shape": "Soft oval", "eye_details": "Glossy reflective eyes with soft cyan and pink highlights, slight moisture for realism", "skin_complexion": "Highly realistic skin with visible pores, subtle imperfections, soft pastel light reflection", "unique_features": "Micro-expression sadness, relaxed lips, natural asymmetry" }, "hair_logic": { "style": "Loose, slightly messy", "texture": "Soft and natural", "color": "Dark brown / black", "physics": "Gentle wind movement, subtle strand separation, soft rim lighting in pastel tones" }, "pose_and_action": { "description": "Standing calmly near rooftop edge", "facial_expression": "Soft, distant, emotionally reflective", "gaze_direction": "Looking toward city, not directly at camera" } }, "wardrobe": { "top": { "type": "Futuristic techwear jacket", "color": "Matte black", "material": "Soft synthetic fabric with light reflective seams", "style": "Minimalist cyberpunk", "details": "Subtle reflective piping catching pastel neon light, slightly oversized fit", "fit": "Relaxed" } }, "typography": { "title_text": { "content": "PAPERCUT", "position": "Behind subject in sky area", "style": "Grunge Bush-style sans-serif (distressed, eroded edges)", "color": "Soft gradient (Pastel Cyan → Soft Pink)", "texture": "Subtle noise + worn texture overlay", "opacity": "Medium-low", "blend_mode": "Screen", "depth_blur": "Slightly out of focus", "effects": "Light glitch flicker + soft neon bleed" }, "artist_label": { "content": "LINKIN PARK", "position": "Right mid", "style": "Bold uppercase grunge sans-serif", "color": "Soft white with slight texture", "opacity": "Medium", "effects": "Very subtle distortion" }, "secondary_text": { "content": "MoonChill • NIGHT MODE • EDM", "position": "Left mid", "style": "Thin modern sans-serif (clean contrast to grunge)", "color": "Pale cyan", "opacity": "Soft" } }, "environment": { "setting_type": "Skyscraper Rooftop", "location_details": "Minimal rooftop edge visible, expansive futuristic skyline with soft holographic lights", "background_chaos": "Smooth bokeh lights, layered haze, diffused neon glow, no harsh shapes" }, "lighting": { "source": "Diffused pastel neon lights from city below", "fill_light": "Soft frontal glow (cool cyan)", "direction": "Soft upward ambient + gentle side rim lighting", "quality": "Very soft, cinematic, diffused", "shadows": "Soft and natural", "highlights": "Subtle pastel rim light on hair and cheekbones" }, "cinematography": { "optical_physics": { "lens_distortion": "Minimal", "chromatic_aberration": "Very subtle", "bokeh_style": "Creamy circular bokeh" }, "shutter_mechanics": { "motion_blur": "Very minimal" } }, "tech_specs": { "iso": "400", "aperture": "f/1.6", "focal_length": "50mm", "shutter_speed": "1/125s" }, "technical_imperfections": { "focus": "Eyes critically sharp", "sensor_noise": "Fine film grain", "digital_processing": "Soft bloom, pastel grading, slight RGB split, natural skin rendering" }, "final_prompts": { "positive": "ultra realistic cinematic portrait of a young woman on a rooftop at night, soft pastel cyberpunk city lights in cyan pink and lavender, dreamy atmosphere, gentle wind in hair, natural skin texture, shallow depth of field, creamy bokeh, soft neon reflections, emotional expression, music cover aesthetic, grunge style text PAPERCUT, LINKIN PARK, subtle glitch, photorealistic, cinematic lighting", "negative": "anime, cartoon, cgi, overexposed neon, harsh contrast, yellow dominant lighting, plastic skin, unrealistic proportions, watermark" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised hand.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a tight closed fist, with the palm side facing the camera so that the curled fingers and the inner part of the hand are clearly visible. The back of the hand is not dominant. The fingers are fully curled, and the fist looks natural, clean, and confident. The thumb is folded over the other fingers (or placed naturally, not extended). No thumbs‑up, no OK sign, no open palm.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the clenched fist; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, fist edges, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, thumbs up, OK sign, peace sign, pointing, back of hand dominant)", "deformed hands", "extra fingers", "missing fingers", "blurred fist", "flat palm", "knuckles emphasized" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "thumbs up", "ok gesture", "peace sign", "pointing", "back of hand facing camera", "unnatural fist", "broken wrist", "blurred hands", "bad anatomy", "twisted fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a luxury nightclub VIP booth, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (burgundy quilted walls, black leather furniture) is heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, fabric details, paper money texture, and tattoos – all rendered with natural grain and no smoothing. The composition is a high‑angle shot (top‑down), slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a luxury nightlife, flex culture atmosphere.", "scene": { "location": "Nightclub VIP zone, dark interior, black leather couch with diamond tufting, burgundy soft panel walls with diamond quilting, low ceiling. The floor is covered with scattered US dollar bills. A few glasses and club table in the background, heavily darkened.", "protagonists": { "woman_left": { "position": "Sitting on the left side of the couch, body turned slightly toward camera (~15°), leaning forward. Head lifted, looking upward directly at the camera. Expression: serious, neutral‑dominant, eyes slightly narrowed. Wears a dark fitted top (black) and light grey/white jeans. Metallic strappy sandals. Skin has visible pores and subtle sweat sheen from flash. Hair dark, slightly messy." }, "woman_right": { "position": "Sitting on the right side, body in half‑turn, leaning forward slightly, head raised and turned ~10‑15° toward camera. Expression: playful pout (duck face), lips pursed. Wears a black strapless dress/smooth synthetic fabric. A thin bracelet on wrist, a small tattoo visible on shoulder/collarbone area. Hair dark." } }, "foreground_arm": { "description": "A male arm (tattooed forearm) extending from the lower left corner, holding several thick stacks of US dollar bills (rubber bands visible). The arm creates a diagonal across the frame. The forearm has multiple tattoos, a few bracelets, and a watch. The hand grips the money tightly, fingers showing slight shadows from the flash." }, "money": { "description": "Large amount of US dollar bills scattered on the couch, on the women's laps, and on the floor. The bills are wrinkled, some folded, with visible texture and greenish‑yellow color. The flash creates overexposed highlights on the glossy parts of the notes." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient club light visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on skin (forehead, nose, shoulders), on the money stacks, on the leather couch reflections; deep black shadows in the background and under the women's chins.", "effects": [ "strong, direct flash creating hard specular highlights on the skin, the glossy leather, the metallic sandals, the watch crystal, and the money", "background very dark – the burgundy walls appear almost black, the black leather couch is barely visible except for bright highlights on the tufting", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash, the green of the dollar bills is muted, almost greyish‑green", "extremely high contrast – bright white highlights next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (money edges, women's hair, arm contours)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The dollar bills lose their saturated green, appearing pale olive. Skin tones are pale with a cool undertone.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "High‑angle shot (~50‑70° downward), camera positioned above the subjects, slightly tilted (Dutch angle ~5‑10°). Camera distance to the foreground arm ~25‑35 cm, to the women's faces ~70‑100 cm. Wide‑angle equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "vertical 4:5, medium‑close shot, the two women fill the center and middle, the arm and money in the lower left foreground, the background and floor fill the rest. Headroom minimal, composition dense.", "focus": "slightly soft, typical of flash photography, the foreground arm and money are relatively sharp, the women's faces slightly softer, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid VIP nightclub snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, sweat, fine hairs, freckles)", "visible fabric texture (denim, synthetic top)", "paper money texture (wrinkles, folds, edge roughness)", "tattoo details", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible face of the male arm owner", "excessive cle**", "explicit nudity" ] }, "negative_prompt": [ "different characters", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "HDR look", "saturated colors", "clear faces without shine" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "16:9", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at night in a vast windswept grass field, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (distant horizon, sky, faint stars) is heavily darkened but faintly visible. Ultra‑realistic textures of grass, fabric, and soil – all rendered with natural grain and no smoothing. The composition is centered, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, mysterious, unsettling, with a paranormal, liminal space atmosphere.", "scene": { "location": "Vast open moorland or grass field at night. Tall wild grass (height ~40‑80 cm) bending strongly in the wind, creating flowing waves. The ground is uneven, with natural bumps and dips. The horizon is low (upper third of the frame). The sky is dark, with very faint stars barely visible, completely darkened by the flash. The wind is strong and constant, making the grass lean uniformly to one side.", "subject": { "description": "A tall, slender human figure standing motionless in the center of the frame, facing the camera directly (front view). The figure is completely overexposed by the harsh flash – its entire body glows pure white, with no discernible facial features, clothing details, or texture. The silhouette resembles a long, loose robe or mantle that reaches the ground, with a straight, free‑flowing cut. The arms are straight down along the body, hands at thigh level. The figure appears to be unnaturally bright, as if emitting light, but it's actually the flash blowing out all detail. The outline is sharp against the dark background, with a slight halo effect (halation) from the flash.", "pose": "Standing upright, perfectly centered, weight evenly distributed, head straight, arms relaxed at sides." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient night light is visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the figure (pure white, blown out), deep black shadows in the background and under the figure.", "effects": [ "strong, direct flash creating a pure white silhouette of the figure, completely devoid of texture or facial features", "the flash creates a sharp, crisp shadow of the figure on the grass behind it (visible on the ground)", "the grass in the immediate foreground (within 1‑2 meters of the camera) is also overexposed, with bright highlights on individual blades", "background very dark – the horizon line is barely visible as a faint dark band, the sky is pitch black, stars not visible", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass appears pale olive‑green, almost grey; the white figure is pure white; the sky is black", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (figure outline, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The grass loses its warm green, appearing pale and cool. The figure is pure white with a slight blue tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, eye level (camera height approx. 1.5‑1.7 m), centered composition. Full‑body shot (figure from head to feet). Camera distance ~15‑20 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35‑50mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "horizontal 16:9, wide shot, subject centered, slight tilt (~2‑3°), a small intruding element (a blade of grass or a strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the figure and the immediate grass are relatively sharp, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid paranormal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white silhouette)", "harsh shadows with no detail", "pitch black background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, bending in wind, slight motion blur)", "chromatic aberration", "barrel distortion", "lens flare", "halation around the figure" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint horizon)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin (no skin visible)", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "any clothing details on the figure", "bloom (except flash halation)", "soft glow (the figure must be pure white overexposed, not a gentle glow)" ] }, "negative_prompt": [ "different composition", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic) – but here overexposed is desired, so only excessive overexposure that destroys shape? Actually we want blown highlights but the figure's outline must remain clear. So careful: the figure should be pure white but the edges should be visible.", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint horizon)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional motion blur)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background", "HDR look", "saturated colors", "bloom (except flash halation)", "soft glow", "facial recognition" ] }
{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } } { "subject": { "demographics": "Young adult female, light skin tone with visible tan lines.", "hair": "Platinum blonde hair with distinct dark roots, styled in a messy high bun, loose strands framing the face.", "apparel": "Black strapless bandeau top, minimally visible matching black bottoms.", "accessories": "Large silver hoop earrings, thin silver chain necklace with a star pendant.", "anatomy": "Full, heavy bust with natural gravitational weight due to forward-leaning pose. Visible cleavage and soft tissue volume. Clear tan lines on the upper chest indicating previous sun exposure with a different top.", "skin_details": "Wet, glistening skin texture with visible water droplets. High-resolution pores and skin imperfections. Reflective sheen on shoulders, chest, and face." }, "pose": { "body_position": "Deep squatting/crouching position on the floor. Knees bent deeply outward.", "orientation": "Facing the camera, body leaning forward.", "limbs": "Right arm extended towards the camera (suggesting a selfie angle). Left arm reaching down, hand resting on the floor between the feet.", "head_and_gaze": "Head tilted slightly downward, chin tucked. Eyes looking upward directly into the camera lens with a focused expression." }, "environment": { "setting": "Tiled shower stall or bathroom corner.", "background_elements": "Grey square tiles on walls and floor. Chrome shower mixer/handle visible on the right wall. A white towel hanging on the left side.", "surface_interaction": "Floor tiles appear wet. Water reflections visible on the ground." }, "camera": { "perspective": "High-angle, top-down perspective (selfie style).", "shot_type": "Close-up, full body from a high angle (head to feet visible due to compression).", "focal_length": "Wide-angle lens, creating slight perspective distortion where the head and upper body appear larger than the feet.", "depth_of_field": "Deep depth of field, keeping both the face and the tiled floor in focus." }, "lighting": { "source": "Bright, artificial overhead bathroom lighting.", "quality": "Harsh, direct light creating strong specular highlights on the wet skin (forehead, nose, shoulders, chest).", "shadows": "Deep, sharp shadows cast by the body onto the floor and under the chin/neck area." }, "mood_and_expression": { "emotion": "Candid, intense, slightly provocative but casual.", "facial_expression": "Pouting lips, relaxed facial muscles, piercing upward gaze." }, "style_and_realism": { "aesthetic": "Raw, unfiltered phone photography. Amateur selfie aesthetic.", "fidelity": "Photorealistic, high-fidelity skin texture. No airbrushing or artistic stylization." }, "colors_and_tone": { "palette": "Neutral greys (tiles), skin tones (tan and pale), stark black (clothing), silver (accessories).", "contrast": "High contrast due to bright overhead light and dark shadows.", "saturation": "Natural, slightly muted background with warm skin tones." }, "quality_and_technical_details": { "resolution": "High definition, sharp focus.", "texture_emphasis": "Emphasis on wet skin, hair strands, and tile grout." }, "aspect_ratio_and_output": { "ratio": "3:4", "framing": "Vertical orientation." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve deep squat position", "preserve forward lean angle", "preserve arm extension for selfie perspective", "preserve head tilt and upward gaze" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve high-angle foreshortening", "maintain chest foreground dominance", "prevent flattening of the squat posture" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or artificially supported breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "dry skin", "standing pose" ] } }{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } }{ "subject": { "description": "Young woman with fair skin and long, straight brunette hair parted in the middle. She has almond-shaped hazel-green eyes, a refined nose, and full pink lips with a subtle gloss. She is wearing a tight, blue floral-print halter-neck one-piece swimsuit or bodysuit featuring bright pink flowers and green leaves. The garment has a deep plunging neckline that reveals significant cleavage.", "anatomy_and_proportions": "The subject possesses an extremely voluptuous and heavy bust that is significantly above average in volume. The chest mass is full, projecting forward and outward, heavily affected by gravity due to natural weight. The bust depth is visibly greater than the ribcage depth. The torso is slender, creating a dramatic bust-to-waist ratio. Skin texture is natural with visible pores, faint freckles, and soft tissue volume.", "clothing_fit": "The floral bodysuit fits tightly against the skin, conforming to the heavy curvature of the chest and waist. The fabric is strained slightly by the volume of the bust. Thin halter straps go around the neck." }, "pose": { "stance": "Standing upright with a relaxed posture.", "head_position": "Head is tilted slightly downward, with the chin tucked in, looking up towards the camera through eyelashes.", "limbs": "Arms are extended downwards along the sides of the body, relaxed and out of the primary focal area.", "orientation": "Body is facing forward towards the camera, with a slight, subtle angle." }, "environment": { "location": "A domestic kitchen interior.", "background_elements": "To the left, a wooden countertop with a mosaic tile backsplash in shades of purple, grey, and white. White cabinetry with black knobs. Kitchen utensils (spatulas, spoons) in a holder. To the right, built-in stainless steel and black double wall ovens. Wooden flooring is visible.", "details": "Modern, clean, well-lit residential setting." }, "camera": { "perspective": "High-angle shot, looking down at the subject.", "framing": "Medium shot, capturing the subject from the mid-thighs up to the top of the head.", "focal_length": "35mm to 50mm, creating a sense of intimacy without excessive distortion.", "depth_of_field": "Subject is in sharp focus; the kitchen background is slightly softened but fully distinct.", "shot_type": "Eye-level relative to the high angle, emphasizing the subject's gaze and upper body volume." }, "lighting": { "source": "Soft, diffuse indoor ambient lighting, likely a mix of overhead kitchen fixtures and natural light.", "direction": "Top-down and slightly frontal.", "shadows": "Soft shadows visible in the cleavage and under the chin, defining the volume of the chest and facial features.", "highlights": "Subtle specular highlights on the forehead, nose, and the curvature of the upper chest.", "quality": "Neutral to slightly cool color temperature." }, "mood_and_expression": { "expression": "Neutral to soft, alluring gaze. Direct eye contact with a slight 'doe-eyed' look due to the camera angle.", "atmosphere": "Casual, candid, intimate, domestic.", "emotion": "Calm and confident." }, "style_and_realism": { "aesthetic": "High-fidelity photorealism, resembling a high-quality smartphone photo or candid DSLR shot.", "texture_quality": "Ultra-detailed skin texture, realistic fabric weave, accurate material rendering for the kitchen surfaces (wood, tile, metal).", "render_style": "Unfiltered, raw, authentic photography style." }, "colors_and_tone": { "palette": "Natural skin tones, vibrant blue and pink on the swimsuit, neutral whites, browns, and mosaic purples in the background.", "contrast": "Moderate contrast, preserving shadow detail in the hair and background.", "saturation": "Natural and lifelike, with the swimsuit colors popping against the neutral kitchen tones." }, "quality_and_technical_details": { "resolution": "8k, high definition.", "sharpness": "Crisp focus on the eyes and face.", "noise": "Low ISO, minimal grain." }, "aspect_ratio_and_output": { "ratio": "3:4", "orientation": "Portrait" }, "controlnet": { "pose_control": { "model_type": "OpenPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock head tilt and chin tuck" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve chest foreground dominance", "prevent flat or compressed depth", "maintain clear torso-to-background separation", "ensure high-angle perspective geometry" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or lifted breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "mirror selfies", "phone-in-hand selfies", "reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "more realistic reinterpretation", "naturalization of prominent features", "low angle", "looking away" ] } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her pose is natural, not overly posed. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised thumb.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a clear, strong thumbs‑up gesture: the fist is tightly closed (all four fingers curled inward), the thumb is extended straight upward, vertical, pointing to the sky. The palm is slightly angled toward the camera (approx. 30‑45°), making the gesture clearly readable. The thumb is well‑defined, no blur.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the raised thumb; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, thumb edge, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, peace sign, OK sign, pointing finger)", "deformed hands", "extra fingers", "missing fingers", "blurred thumb", "thumb not vertical" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "pointing finger", "ok gesture", "peace sign", "blurred hands", "bad anatomy", "twisted fingers", "broken thumb", "unnatural pose", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "meta": { "style": "ultra-realistic beach portrait photography", "quality": "8k high resolution", "camera": "Full-frame DSLR", "lens": "85mm f/1.8 portrait lens", "aperture": "f/2.8", "lighting": "natural golden hour sunset light with soft ambient sky glow", "color_grading": "soft cinematic teal and peach tones", "aspect_ratio": "4:5 vertical", "sharpness": "razor sharp focus on subject, slightly softened background" }, "scene": { "location": "sandy beach shoreline", "environment": "gentle ocean waves rolling in behind subject", "time_of_day": "sunset / early dusk", "sky": "pastel blue sky with subtle pink and lavender sunset hues", "atmosphere": "calm, serene, warm coastal breeze", "background_blur": "moderate shallow depth of field with smooth ocean bokeh" }, "subject": { "gender": "female", "age_range": "mid 20s", "physique": "fit, natural proportions, toned yet soft curves", "skin_tone": "light with natural warm undertones", "skin_texture": "natural skin texture with subtle water sheen", "expression": "gentle confident smile, relaxed and approachable", "eyes": "soft expressive eyes looking directly at camera", "hair": { "color": "dark brown", "style": "long, loose, wet, naturally tousled", "detail": "slightly damp strands resting over shoulders and back" } }, "pose": { "stance": "standing upright on wet sand", "left_hand": "resting naturally on top of head, fingers lightly touching hair", "right_hand": "placed on hip creating confident posture", "body_angle": "slightly angled torso toward camera", "gaze_direction": "direct eye contact with camera" }, "wardrobe": { "outfit_type": "minimal two-piece bikini", "top": { "color": "light beige / off-white", "trim": "green edging", "style": "triangle bikini top with thin straps" }, "bottom": { "color": "light beige / off-white", "trim": "green edging", "style": "low-rise bikini bottom" } }, "composition": { "framing": "mid-thigh up portrait", "focus_priority": "sharp focus on face and upper body", "depth_of_field": "shallow depth for subject isolation", "rule_of_thirds": "subject centered with horizon line slightly above mid-frame", "balance": "symmetrical composition with ocean horizon in background" }, "mood": { "vibe": "fresh, natural, confident summer aesthetic", "emotion": "relaxed, empowered, radiant", "energy": "soft coastal elegance" }, "post_processing": { "retouching": "light professional beauty retouch, preserve natural skin texture", "contrast": "moderate contrast for depth", "highlights": "soft glow on skin highlights", "shadows": "balanced soft shadows", "color_enhancement": "enhanced ocean blues and warm sunset
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a traditional Spanish restaurant in Valencia, evening, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background details (tables, chairs, bar, other diners) are heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, intimate, capturing a spontaneous moment inside a rustic Spanish eatery.", "scene": { "location": "Traditional Spanish restaurant (restaurante español) in Valencia, evening. The interior features dark wooden tables, red or white tablecloths, rustic chairs, and tiled walls with typical Spanish patterns. In the background, a bar area with bottles and a glowing sign that reads 'RESTAURANTE ESPAÑOL' in warm yellow or red neon (or a carved wooden sign). Other diners are blurred and dark. The floor is ceramic tile. The flash darkens most of the background, leaving only the subject and the sign faintly visible.", "restaurant_details": "Wooden beams on ceiling, hanging jamón serrano, clay plates, wine bottles. The sign 'RESTAURANTE ESPAÑOL' is in a traditional font, perhaps with a small Spanish flag or flamenco motif. It catches the flash with a soft glow.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She sits at a small table, facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands falling over her shoulder. She holds a glass of red wine or sangria in one hand, the other hand resting on the table. A small leather bag hangs on the back of her chair. Her pose is natural, leaning slightly forward, weight on one elbow. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the wine glass." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient warm restaurant light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, glass, and the sign; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the restaurant interior is barely visible as faint silhouettes, the sign 'RESTAURANTE ESPAÑOL' glows softly but is dark overall, other diners are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., wine glass rim, hair strands, sign edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm restaurant tones are completely eliminated, leaving only the raw flash color. The sign's warm color is mostly desaturated but retains a hint of its original hue.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Eye‑level, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos (except the restaurant sign)", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her pose is natural, not overly posed. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised thumb.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a clear, strong thumbs‑up gesture: the fist is tightly closed (all four fingers curled inward), the thumb is extended straight upward, vertical, pointing to the sky. The palm is slightly angled toward the camera (approx. 30‑45°), making the gesture clearly readable. The thumb is well‑defined, no blur.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the raised thumb; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, thumb edge, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, peace sign, OK sign, pointing finger)", "deformed hands", "extra fingers", "missing fingers", "blurred thumb", "thumb not vertical" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "pointing finger", "ok gesture", "peace sign", "blurred hands", "bad anatomy", "twisted fingers", "broken thumb", "unnatural pose", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a luxury nightclub VIP booth, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (burgundy quilted walls, black leather furniture) is heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, fabric details, paper money texture, and tattoos – all rendered with natural grain and no smoothing. The composition is a high‑angle shot (top‑down), slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a luxury nightlife, flex culture atmosphere.", "scene": { "location": "Nightclub VIP zone, dark interior, black leather couch with diamond tufting, burgundy soft panel walls with diamond quilting, low ceiling. The floor is covered with scattered US dollar bills. A few glasses and club table in the background, heavily darkened.", "protagonists": { "woman_left": { "position": "Sitting on the left side of the couch, body turned slightly toward camera (~15°), leaning forward. Head lifted, looking upward directly at the camera. Expression: serious, neutral‑dominant, eyes slightly narrowed. Wears a dark fitted top (black) and light grey/white jeans. Metallic strappy sandals. Skin has visible pores and subtle sweat sheen from flash. Hair dark, slightly messy." }, "woman_right": { "position": "Sitting on the right side, body in half‑turn, leaning forward slightly, head raised and turned ~10‑15° toward camera. Expression: playful pout (duck face), lips pursed. Wears a black strapless dress/smooth synthetic fabric. A thin bracelet on wrist, a small tattoo visible on shoulder/collarbone area. Hair dark." } }, "foreground_arm": { "description": "A male arm (tattooed forearm) extending from the lower left corner, holding several thick stacks of US dollar bills (rubber bands visible). The arm creates a diagonal across the frame. The forearm has multiple tattoos, a few bracelets, and a watch. The hand grips the money tightly, fingers showing slight shadows from the flash." }, "money": { "description": "Large amount of US dollar bills scattered on the couch, on the women's laps, and on the floor. The bills are wrinkled, some folded, with visible texture and greenish‑yellow color. The flash creates overexposed highlights on the glossy parts of the notes." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient club light visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on skin (forehead, nose, shoulders), on the money stacks, on the leather couch reflections; deep black shadows in the background and under the women's chins.", "effects": [ "strong, direct flash creating hard specular highlights on the skin, the glossy leather, the metallic sandals, the watch crystal, and the money", "background very dark – the burgundy walls appear almost black, the black leather couch is barely visible except for bright highlights on the tufting", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash, the green of the dollar bills is muted, almost greyish‑green", "extremely high contrast – bright white highlights next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (money edges, women's hair, arm contours)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The dollar bills lose their saturated green, appearing pale olive. Skin tones are pale with a cool undertone.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "High‑angle shot (~50‑70° downward), camera positioned above the subjects, slightly tilted (Dutch angle ~5‑10°). Camera distance to the foreground arm ~25‑35 cm, to the women's faces ~70‑100 cm. Wide‑angle equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "vertical 4:5, medium‑close shot, the two women fill the center and middle, the arm and money in the lower left foreground, the background and floor fill the rest. Headroom minimal, composition dense.", "focus": "slightly soft, typical of flash photography, the foreground arm and money are relatively sharp, the women's faces slightly softer, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid VIP nightclub snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, sweat, fine hairs, freckles)", "visible fabric texture (denim, synthetic top)", "paper money texture (wrinkles, folds, edge roughness)", "tattoo details", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible face of the male arm owner", "excessive cle**", "explicit nudity" ] }, "negative_prompt": [ "different characters", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "HDR look", "saturated colors", "clear faces without shine" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
Scene: Selfie in front of a mirror inside a gym with a wooden floor and workout equipment visible in the background. Atmosphere: Sporty, focused on strength and fitness, with a sense of confidence and a training routine. Style and Aesthetics Visual Style: Minimalist, sporty, realistic, fitness editorial; clean and direct aesthetic. Color Palette: Predominantly black and white in the clothing, warm tones in the wooden floor, and metallic grays in the equipment; moderate contrast between subject and background. Clothing and Accessories Clothing: Black sports bra; black shorts with visible white text that reads PRO NIKE. Footwear and Socks: White sneakers with white socks. Accessories: Smartphone in hand for the selfie; no jewelry or other flashy accessories are visible. Setting and Background Elements Setting: Indoor gym with a wooden floor. Visible Equipment: Weight racks, dumbbells, weight stacks, and resistance bands. Depth: Equipment distributed in the background that provides functional context without distracting from the subject. Pose and Body Language Pose: Confident stance, one hand on the hip and the other holding the phone in front of the face for the selfie. Body Language: Torso slightly turned toward the mirror, weight shifted to one leg, gaze directed at the mirror through the phone; confident and focused demeanor. Lighting Type of light: Gym ambient light, likely a mix of cool artificial lighting and soft ambient light; soft shadows and moderate contrast that define the musculature without being dramatic. Direction: Primarily overhead and frontal light reflected by the mirror, illuminating the face and torso evenly. Angle and Lens Camera angle: Frontal selfie at torso level, slightly above the center of the body for a three-quarter view. Lens type: Short wide-angle smartphone lens appearance, approximately equivalent to 24–35 mm in full-frame, with minimal peripheral distortion and a wide depth of field that keeps the background recognizable. Composition and Technical Details Framing: Subject centered in the mirror, cropped from thigh level to head; Negative space surrounding the gym. Focus: sharp on the subject; background with sufficient detail for context. Texture: the wood of the floor and the metal of the equipment contrast with the matte fabric of the workout clothes. Don't alter my face or my hairstyle
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a bright emerald green supercar on a countryside road, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (trees, road, the second supercar) is heavily darkened but faintly visible. Ultra‑realistic textures of carbon fiber, car paint, asphalt, and skin (if any visible) – all rendered with natural grain and no smoothing. The composition is strongly tilted (Dutch angle ~25‑35°), with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a aggressive, luxury supercar lifestyle vibe.", "scene": { "location": "Countryside asphalt road, overcast daylight but the flash overpowers everything. Surrounding trees (lush green) are almost black silhouettes. The road has visible cracks and wear. In the distance, another bright emerald green supercar (identical or similar) drives ahead, its shape faintly visible, tail lights reflecting the flash as small red dots.", "car_interior": "Inside a supercar. The door panel is visible on the left, covered in glossy carbon fiber (2x2 twill weave pattern) with strong specular highlights from the flash. The windshield and side window show dark silhouettes of trees. The car's exterior hood (emerald green metallic) is visible in the lower left and middle, with blown highlights and dark reflections.", "protagonist": "A person (Welison style, but face fully covered by a glossy carbon fiber full‑face mask) leaning out of the car window or sitting close to the camera. The mask has a aggressive, futuristic design, with narrow eye slits (dark mesh inside). The mask is highly reflective, showing the flash as bright white hotspots. Only the mask, a small part of the shoulder/neck, and a light gray hoodie or t‑shirt collar are visible. The body is turned slightly toward the camera. The mask occupies the lower right third of the frame (approx. 35‑40% of image). The pose is dominant, mysterious, anonymous.", "second_car": "In the upper central background, another emerald green supercar, slightly blurred by motion and heavily darkened, but its shape recognizable, with headlights or taillights catching the flash." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient overcast daylight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the carbon fiber mask, the car’s green paint, the windshield edges, and any reflective surfaces; deep black shadows in the trees and the second car.", "effects": [ "strong, direct flash creating hard specular highlights on the glossy carbon fiber weave (mask and door panel), on the car’s metallic paint, and on the glass", "the background trees become dark silhouettes with no detail, the road surface shows harsh shadows from the flash", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the emerald green becomes a pale, cool green with blue/cyan cast; carbon fiber appears dark grey with bright reflections", "extremely high contrast – bright white hotspots next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (mask edges, car door lines, windshield frame)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky/trees", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The car’s green loses warmth, looking almost teal; the carbon fiber appears cold.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "First‑person / passenger perspective, strong Dutch angle (tilted ~25‑35° counter‑clockwise), camera very close to the mask (approx. 20‑40 cm). Wide‑angle lens equivalent 24‑28mm.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 24‑28mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, extremely tight composition, mask in lower right, car hood in lower left, second car in upper center. Headroom minimal, dense composition.", "focus": "slightly soft, typical of flash photography, the mask and the immediate car interior are relatively sharp, background and second car out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid supercar snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (strong tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "visible carbon fiber weave texture with glossy reflections", "metallic car paint with blown highlights", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint outlines)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "skin on face or neck (only covered by mask)", "matte plastic mask" ] }, "negative_prompt": [ "different character", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint outlines)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture (except carbon fiber mask)", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky", "detailed background", "HDR look", "saturated greens" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background" ] }
{ "meta": { "aesthetic_goal": "Ultra Realistic Cinematic Music Cover / Soft Cyberpunk Pastel", "vibe_mode": "Dreamy Rooftop Night / Soft Neon Atmosphere", "image_quality": "Ultra High / Photorealistic Album Cover", "image_type": "Photo", "device_simulation": "Full-frame mirrorless cinematic portrait", "render_settings": { "resolution": "1792x1024", "aspect_ratio": "16:9", "quality_tags": "ultra realistic, pastel cyberpunk, soft glow, cinematic lighting, shallow depth of field, film grain, high dynamic range" } }, "global_context": { "scene_description": "A highly realistic cinematic portrait of a young woman standing on a skyscraper rooftop at night, overlooking a dreamy cyberpunk city filled with soft pastel neon lights (muted cyan, soft pink, lavender, pale amber).", "time_of_day": "Late Night", "weather_atmosphere": "Cool air, gentle wind, thin mist, diffused neon haze, soft atmospheric bloom" }, "artistic_elements": { "mood": "Quiet, emotional, introspective, slightly melancholic but peaceful", "style": "Soft Cyberpunk Realism / Dreamwave", "theme": "Loneliness in a connected world", "narrative": "A solitary figure observing a calm futuristic city glowing softly beneath, representing emotional distance softened by quiet acceptance.", "compositional_technique": "Centered subject with layered depth (foreground softness, mid subject sharp, background blur)", "authenticity_marker": "natural skin texture, subtle wind motion, realistic light falloff, soft RGB split, cinematic imperfections" }, "color_palette": { "dominant_hex_estimates": [ "#0e1117", "#10131c" ], "accent_colors": [ "Soft Cyan", "Pastel Pink", "Lavender Purple", "Muted Amber Highlights" ], "contrast_level": "Medium-Low", "overall_mood": "Dark base with gentle pastel neon glow" }, "composition": { "layout_type": "Music Cover", "camera_angle": "Eye Level", "framing": "Waist Up", "depth_of_field": "Very shallow (creamy bokeh city lights)", "focal_point": "Eyes", "balance": "Centered with subtle asymmetry from city lights", "key_elements": [ "Emotional eyes with soft reflections", "Rooftop edge slightly visible", "Dreamy skyline bokeh", "Soft neon reflections on skin", "Floating typography" ] }, "subject_analysis": { "identity_summary": "Young woman (20-25), calm, introspective, emotionally distant yet peaceful", "visual_signature": { "face_shape": "Soft oval", "eye_details": "Glossy reflective eyes with soft cyan and pink highlights, slight moisture for realism", "skin_complexion": "Highly realistic skin with visible pores, subtle imperfections, soft pastel light reflection", "unique_features": "Micro-expression sadness, relaxed lips, natural asymmetry" }, "hair_logic": { "style": "Loose, slightly messy", "texture": "Soft and natural", "color": "Dark brown / black", "physics": "Gentle wind movement, subtle strand separation, soft rim lighting in pastel tones" }, "pose_and_action": { "description": "Standing calmly near rooftop edge", "facial_expression": "Soft, distant, emotionally reflective", "gaze_direction": "Looking toward city, not directly at camera" } }, "wardrobe": { "top": { "type": "Futuristic techwear jacket", "color": "Matte black", "material": "Soft synthetic fabric with light reflective seams", "style": "Minimalist cyberpunk", "details": "Subtle reflective piping catching pastel neon light, slightly oversized fit", "fit": "Relaxed" } }, "typography": { "title_text": { "content": "PAPERCUT", "position": "Behind subject in sky area", "style": "Grunge Bush-style sans-serif (distressed, eroded edges)", "color": "Soft gradient (Pastel Cyan → Soft Pink)", "texture": "Subtle noise + worn texture overlay", "opacity": "Medium-low", "blend_mode": "Screen", "depth_blur": "Slightly out of focus", "effects": "Light glitch flicker + soft neon bleed" }, "artist_label": { "content": "LINKIN PARK", "position": "Right mid", "style": "Bold uppercase grunge sans-serif", "color": "Soft white with slight texture", "opacity": "Medium", "effects": "Very subtle distortion" }, "secondary_text": { "content": "MoonChill • NIGHT MODE • EDM", "position": "Left mid", "style": "Thin modern sans-serif (clean contrast to grunge)", "color": "Pale cyan", "opacity": "Soft" } }, "environment": { "setting_type": "Skyscraper Rooftop", "location_details": "Minimal rooftop edge visible, expansive futuristic skyline with soft holographic lights", "background_chaos": "Smooth bokeh lights, layered haze, diffused neon glow, no harsh shapes" }, "lighting": { "source": "Diffused pastel neon lights from city below", "fill_light": "Soft frontal glow (cool cyan)", "direction": "Soft upward ambient + gentle side rim lighting", "quality": "Very soft, cinematic, diffused", "shadows": "Soft and natural", "highlights": "Subtle pastel rim light on hair and cheekbones" }, "cinematography": { "optical_physics": { "lens_distortion": "Minimal", "chromatic_aberration": "Very subtle", "bokeh_style": "Creamy circular bokeh" }, "shutter_mechanics": { "motion_blur": "Very minimal" } }, "tech_specs": { "iso": "400", "aperture": "f/1.6", "focal_length": "50mm", "shutter_speed": "1/125s" }, "technical_imperfections": { "focus": "Eyes critically sharp", "sensor_noise": "Fine film grain", "digital_processing": "Soft bloom, pastel grading, slight RGB split, natural skin rendering" }, "final_prompts": { "positive": "ultra realistic cinematic portrait of a young woman on a rooftop at night, soft pastel cyberpunk city lights in cyan pink and lavender, dreamy atmosphere, gentle wind in hair, natural skin texture, shallow depth of field, creamy bokeh, soft neon reflections, emotional expression, music cover aesthetic, grunge style text PAPERCUT, LINKIN PARK, subtle glitch, photorealistic, cinematic lighting", "negative": "anime, cartoon, cgi, overexposed neon, harsh contrast, yellow dominant lighting, plastic skin, unrealistic proportions, watermark" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "16:9", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken at night in a vast windswept grass field, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background (distant horizon, sky, faint stars) is heavily darkened but faintly visible. Ultra‑realistic textures of grass, fabric, and soil – all rendered with natural grain and no smoothing. The composition is centered, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, mysterious, unsettling, with a paranormal, liminal space atmosphere.", "scene": { "location": "Vast open moorland or grass field at night. Tall wild grass (height ~40‑80 cm) bending strongly in the wind, creating flowing waves. The ground is uneven, with natural bumps and dips. The horizon is low (upper third of the frame). The sky is dark, with very faint stars barely visible, completely darkened by the flash. The wind is strong and constant, making the grass lean uniformly to one side.", "subject": { "description": "A tall, slender human figure standing motionless in the center of the frame, facing the camera directly (front view). The figure is completely overexposed by the harsh flash – its entire body glows pure white, with no discernible facial features, clothing details, or texture. The silhouette resembles a long, loose robe or mantle that reaches the ground, with a straight, free‑flowing cut. The arms are straight down along the body, hands at thigh level. The figure appears to be unnaturally bright, as if emitting light, but it's actually the flash blowing out all detail. The outline is sharp against the dark background, with a slight halo effect (halation) from the flash.", "pose": "Standing upright, perfectly centered, weight evenly distributed, head straight, arms relaxed at sides." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). No ambient night light is visible. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the figure (pure white, blown out), deep black shadows in the background and under the figure.", "effects": [ "strong, direct flash creating a pure white silhouette of the figure, completely devoid of texture or facial features", "the flash creates a sharp, crisp shadow of the figure on the grass behind it (visible on the ground)", "the grass in the immediate foreground (within 1‑2 meters of the camera) is also overexposed, with bright highlights on individual blades", "background very dark – the horizon line is barely visible as a faint dark band, the sky is pitch black, stars not visible", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass appears pale olive‑green, almost grey; the white figure is pure white; the sky is black", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (figure outline, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The grass loses its warm green, appearing pale and cool. The figure is pure white with a slight blue tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, eye level (camera height approx. 1.5‑1.7 m), centered composition. Full‑body shot (figure from head to feet). Camera distance ~15‑20 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35‑50mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 400‑800 with heavy grain.", "framing": "horizontal 16:9, wide shot, subject centered, slight tilt (~2‑3°), a small intruding element (a blade of grass or a strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the figure and the immediate grass are relatively sharp, background out of focus and black.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid paranormal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white silhouette)", "harsh shadows with no detail", "pitch black background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, bending in wind, slight motion blur)", "chromatic aberration", "barrel distortion", "lens flare", "halation around the figure" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint horizon)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin (no skin visible)", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features", "any clothing details on the figure", "bloom (except flash halation)", "soft glow (the figure must be pure white overexposed, not a gentle glow)" ] }, "negative_prompt": [ "different composition", "face visible", "facial features", "eyes visible", "mouth visible", "skin on face", "skin on neck", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic) – but here overexposed is desired, so only excessive overexposure that destroys shape? Actually we want blown highlights but the figure's outline must remain clear. So careful: the figure should be pure white but the edges should be visible.", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint horizon)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional motion blur)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight", "no flash look", "bright sky", "detailed background", "HDR look", "saturated colors", "bloom (except flash halation)", "soft glow", "facial recognition" ] }
{ "meta": { "style": "ultra-realistic beach portrait photography", "quality": "8k high resolution", "camera": "Full-frame DSLR", "lens": "85mm f/1.8 portrait lens", "aperture": "f/2.8", "lighting": "natural golden hour sunset light with soft ambient sky glow", "color_grading": "soft cinematic teal and peach tones", "aspect_ratio": "4:5 vertical", "sharpness": "razor sharp focus on subject, slightly softened background" }, "scene": { "location": "sandy beach shoreline", "environment": "gentle ocean waves rolling in behind subject", "time_of_day": "sunset / early dusk", "sky": "pastel blue sky with subtle pink and lavender sunset hues", "atmosphere": "calm, serene, warm coastal breeze", "background_blur": "moderate shallow depth of field with smooth ocean bokeh" }, "subject": { "gender": "female", "age_range": "mid 20s", "physique": "fit, natural proportions, toned yet soft curves", "skin_tone": "light with natural warm undertones", "skin_texture": "natural skin texture with subtle water sheen", "expression": "gentle confident smile, relaxed and approachable", "eyes": "soft expressive eyes looking directly at camera", "hair": { "color": "dark brown", "style": "long, loose, wet, naturally tousled", "detail": "slightly damp strands resting over shoulders and back" } }, "pose": { "stance": "standing upright on wet sand", "left_hand": "resting naturally on top of head, fingers lightly touching hair", "right_hand": "placed on hip creating confident posture", "body_angle": "slightly angled torso toward camera", "gaze_direction": "direct eye contact with camera" }, "wardrobe": { "outfit_type": "minimal two-piece bikini", "top": { "color": "light beige / off-white", "trim": "green edging", "style": "triangle bikini top with thin straps" }, "bottom": { "color": "light beige / off-white", "trim": "green edging", "style": "low-rise bikini bottom" } }, "composition": { "framing": "mid-thigh up portrait", "focus_priority": "sharp focus on face and upper body", "depth_of_field": "shallow depth for subject isolation", "rule_of_thirds": "subject centered with horizon line slightly above mid-frame", "balance": "symmetrical composition with ocean horizon in background" }, "mood": { "vibe": "fresh, natural, confident summer aesthetic", "emotion": "relaxed, empowered, radiant", "energy": "soft coastal elegance" }, "post_processing": { "retouching": "light professional beauty retouch, preserve natural skin texture", "contrast": "moderate contrast for depth", "highlights": "soft glow on skin highlights", "shadows": "balanced soft shadows", "color_enhancement": "enhanced ocean blues and warm sunset
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "iPhone 5 front/back camera aesthetic with harsh on‑camera LED flash, 8MP sensor, grainy texture, moderate compression artifacts, slightly soft details, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited smartphone flash photograph taken at the City of Arts and Sciences (Ciudad de las Artes y las Ciencias) in Valencia, Spain, during early evening (golden hour fading), using an iPhone 5. The LED flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background architecture (the futuristic buildings of Santiago Calatrava) is heavily darkened but faintly visible – the white curved structures become pale silhouettes against the darkening sky. Skin texture is visible but not overly sharp, with natural pores, fine hairs, and imperfections – typical of 8MP smartphone quality. The composition is slightly tilted, with slight vertical banding noise, a minor lens reflection, and a subtle vignette – all adding authentic iPhone 5 camera character. The scene is warm, lively, yet raw and candid, capturing a spontaneous moment in front of iconic Valencian architecture.", "scene": { "location": "City of Arts and Sciences, Valencia, Spain. Early evening, golden hour fading. The background features the iconic futuristic white structures designed by Santiago Calatrava: the Hemisfèric (eye-shaped building), the Museu de les Ciències Príncipe Felipe (whale‑skeleton-like museum), and the Umbracle (garden walkway). The sky is pale blue turning to warm orange near the horizon, but heavily darkened by the flash. Some other tourists are blurred in the background, out of focus. The ground is light stone or pavement, with harsh shadows.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands blown by a light breeze. She holds a straw hat in one hand, the other hand resting on her hip. A small crossbody leather bag is over her shoulder. Her pose is natural, not overly posed – weight on one leg, slight tilt of the head. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow, but with typical smartphone softness. The flash creates specular highlights on her shoulders, collarbones, and the straw hat. In the background, the Calatrava buildings rise behind her – their curved white surfaces catch faint ambient light but are mostly dark silhouettes." }, "lighting_and_atmosphere": { "source": "iPhone 5 LED FLASH ONLY. The ambient dusk/golden hour light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "harsh flash with high contrast, specular highlights on skin, hair, and hat; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face. The image has moderate grain and softness typical of 8MP sensor.", "effects": [ "strong, direct LED flash creating hard specular highlights on every sweat droplet and skin texture, but not razor‑sharp", "background very dark – the Calatrava buildings are barely visible as faint white silhouettes against the sky, other tourists are dark blurry shapes", "grainy texture typical of iPhone 5 at ISO 400‑800 (heavy grain in shadows, fine grain in highlights, slight chroma noise)", "washed out colors, skin tones pale with a slight blue/green cast from the LED flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hat rim, hair strands, building edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding noise visible in the dark sky", "a minor lens reflection (ghosting) in the upper left corner", "subtle vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of iPhone 5 flash. The warm sunset tones are completely eliminated, leaving only the raw flash color. The white Calatrava structures appear with a faint cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, iPhone 5 (8MP sensor, f/2.4 lens, LED flash), 33mm equivalent, autofocus with slight softness, shutter speed 1/60s, ISO 400‑800 with visible grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, minor lens reflection.", "focus": "slightly soft, typical of smartphone flash photography, the subject’s face and upper body are relatively sharp but not clinical, background out of focus and very dark.", "visual_fidelity": "grainy, moderate resolution (8MP) aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic iPhone 5 camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens reflection, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs) but not overly sharp", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical sharpness)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR (iPhone 5 had no HDR+ or deep fusion)", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "too much detail", "oversharpened" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone (newer models)", "LED flash (allowed, but only as iPhone 5 LED)", "modern smartphone (iPhone 6 and above)", "daylight", "no flash look", "bright sky", "detailed background", "excessive sharpness", "high megapixel look" ] }
{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } } { "subject": { "demographics": "Young adult female, light skin tone with visible tan lines.", "hair": "Platinum blonde hair with distinct dark roots, styled in a messy high bun, loose strands framing the face.", "apparel": "Black strapless bandeau top, minimally visible matching black bottoms.", "accessories": "Large silver hoop earrings, thin silver chain necklace with a star pendant.", "anatomy": "Full, heavy bust with natural gravitational weight due to forward-leaning pose. Visible cleavage and soft tissue volume. Clear tan lines on the upper chest indicating previous sun exposure with a different top.", "skin_details": "Wet, glistening skin texture with visible water droplets. High-resolution pores and skin imperfections. Reflective sheen on shoulders, chest, and face." }, "pose": { "body_position": "Deep squatting/crouching position on the floor. Knees bent deeply outward.", "orientation": "Facing the camera, body leaning forward.", "limbs": "Right arm extended towards the camera (suggesting a selfie angle). Left arm reaching down, hand resting on the floor between the feet.", "head_and_gaze": "Head tilted slightly downward, chin tucked. Eyes looking upward directly into the camera lens with a focused expression." }, "environment": { "setting": "Tiled shower stall or bathroom corner.", "background_elements": "Grey square tiles on walls and floor. Chrome shower mixer/handle visible on the right wall. A white towel hanging on the left side.", "surface_interaction": "Floor tiles appear wet. Water reflections visible on the ground." }, "camera": { "perspective": "High-angle, top-down perspective (selfie style).", "shot_type": "Close-up, full body from a high angle (head to feet visible due to compression).", "focal_length": "Wide-angle lens, creating slight perspective distortion where the head and upper body appear larger than the feet.", "depth_of_field": "Deep depth of field, keeping both the face and the tiled floor in focus." }, "lighting": { "source": "Bright, artificial overhead bathroom lighting.", "quality": "Harsh, direct light creating strong specular highlights on the wet skin (forehead, nose, shoulders, chest).", "shadows": "Deep, sharp shadows cast by the body onto the floor and under the chin/neck area." }, "mood_and_expression": { "emotion": "Candid, intense, slightly provocative but casual.", "facial_expression": "Pouting lips, relaxed facial muscles, piercing upward gaze." }, "style_and_realism": { "aesthetic": "Raw, unfiltered phone photography. Amateur selfie aesthetic.", "fidelity": "Photorealistic, high-fidelity skin texture. No airbrushing or artistic stylization." }, "colors_and_tone": { "palette": "Neutral greys (tiles), skin tones (tan and pale), stark black (clothing), silver (accessories).", "contrast": "High contrast due to bright overhead light and dark shadows.", "saturation": "Natural, slightly muted background with warm skin tones." }, "quality_and_technical_details": { "resolution": "High definition, sharp focus.", "texture_emphasis": "Emphasis on wet skin, hair strands, and tile grout." }, "aspect_ratio_and_output": { "ratio": "3:4", "framing": "Vertical orientation." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve deep squat position", "preserve forward lean angle", "preserve arm extension for selfie perspective", "preserve head tilt and upward gaze" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve high-angle foreshortening", "maintain chest foreground dominance", "prevent flattening of the squat posture" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or artificially supported breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "dry skin", "standing pose" ] } }{ "subject": { "description": "Young woman with a curvy, athletic physique, captured from the rear and side profile.", "hair": "Long, dark, voluminous curly hair cascading down the back, reaching mid-back length, with distinct ringlets.", "apparel_top": "Backless reddish-brown or maroon halter top that exposes the entire back. Features a delicate, decorative metallic chain strap running vertically down the spine with small bead-like embellishments.", "apparel_bottom": "Light wash blue denim jeans, tight-fitting to accentuate the glutes and hips, featuring distinct back pocket stitching (American Eagle style stitching visible).", "body_features": "Tan skin tone with visible natural skin texture. Prominent hip-to-waist ratio, very curvy silhouette with emphasized glutes. Toned back muscles visible due to the open back of the top.", "face": "Side profile visible, looking towards the phone screen. Sharp jawline, neutral expression, soft makeup." }, "pose": { "orientation": "Standing with back primarily towards the mirror, twisted slightly to the right to show profile.", "head": "Turned to the right, eyes focused on the phone screen in the reflection.", "arms": "Right arm raised, elbow bent, hand holding a white smartphone to take the photo. Left arm relaxed by the side.", "torso": "Arching slightly to accentuate the lower back curve.", "legs": "Hips shifted to emphasize curves, standing posture.", "hands": "Right hand visible holding the phone, manicured nails (white or light tips)." }, "environment": { "setting": "Indoor room, likely a bedroom.", "background_left": "A wooden door with horizontal paneling and a silver doorknob.", "background_right": "White wall featuring a framed artwork with a black frame and a botanical print (leaves). Below the art, a white shelf or surface with a round woven macramé placemat or rug.", "foreground_details": "The bottom edge of the mirror is visible, showing white electrical outlets with switches on the wall below the mirror reflection." }, "camera": { "shot_type": "Mirror selfie, medium shot capturing from mid-thigh to top of head.", "perspective": "Reflected perspective, camera is the phone seen in the image.", "device": "White smartphone (iPhone style) with a case featuring a black heart or text design, held in the right hand.", "focal_length": "Standard mobile wide lens (approx 26mm equivalent).", "framing": "Vertical framing." }, "lighting": { "source": "Soft, diffused natural light coming from the front (behind the mirror) and ambient room lighting.", "quality": "Even illumination, soft shadows on the back and jeans, highlighting the contours of the body and fabric textures.", "shadows": "Subtle shadows defining the spinal groove and muscle definition on the back." }, "mood_and_expression": { "vibe": "Casual, confident, self-assured.", "expression": "Focused, neutral, checking appearance in the mirror." }, "style_and_realism": { "style": "Photorealistic, user-generated content (UGC) style, high-resolution social media photo.", "fidelity": "High fidelity to textures (denim, skin, hair, wood grain).", "rendering": "Unfiltered, naturalistic appearance." }, "colors_and_tone": { "palette": "Natural earth tones (wood brown, maroon top, tan skin), contrasted with light denim blue and white walls.", "white_balance": "Neutral, slightly warm.", "contrast": "Medium contrast, preserving details in both the dark hair and bright white phone." }, "quality_and_technical_details": { "resolution": "High quality, sharp focus on the subject.", "noise": "Low distinct noise, slight digital grain typical of smartphone photography in indoor light.", "sharpness": "Sharp details on the hair curls and denim texture." }, "aspect_ratio_and_output": { "aspect_ratio": "3:4", "cropping": "Framed to include the head, torso, and upper legs/hips." }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock arm position holding phone" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve foreground dominance of subject", "maintain separation between subject and background elements (door, wall art)", "prevent flat depth" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "flattened curves", "reduced hip volume", "slimmed glutes", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "missing phone", "missing mirror reflection", "facing forward", "direct eye contact with lens (must look at screen)", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "distorted fingers", "bad hands", "extra limbs" ] } }{ "subject": { "description": "Young woman with fair skin and long, straight brunette hair parted in the middle. She has almond-shaped hazel-green eyes, a refined nose, and full pink lips with a subtle gloss. She is wearing a tight, blue floral-print halter-neck one-piece swimsuit or bodysuit featuring bright pink flowers and green leaves. The garment has a deep plunging neckline that reveals significant cleavage.", "anatomy_and_proportions": "The subject possesses an extremely voluptuous and heavy bust that is significantly above average in volume. The chest mass is full, projecting forward and outward, heavily affected by gravity due to natural weight. The bust depth is visibly greater than the ribcage depth. The torso is slender, creating a dramatic bust-to-waist ratio. Skin texture is natural with visible pores, faint freckles, and soft tissue volume.", "clothing_fit": "The floral bodysuit fits tightly against the skin, conforming to the heavy curvature of the chest and waist. The fabric is strained slightly by the volume of the bust. Thin halter straps go around the neck." }, "pose": { "stance": "Standing upright with a relaxed posture.", "head_position": "Head is tilted slightly downward, with the chin tucked in, looking up towards the camera through eyelashes.", "limbs": "Arms are extended downwards along the sides of the body, relaxed and out of the primary focal area.", "orientation": "Body is facing forward towards the camera, with a slight, subtle angle." }, "environment": { "location": "A domestic kitchen interior.", "background_elements": "To the left, a wooden countertop with a mosaic tile backsplash in shades of purple, grey, and white. White cabinetry with black knobs. Kitchen utensils (spatulas, spoons) in a holder. To the right, built-in stainless steel and black double wall ovens. Wooden flooring is visible.", "details": "Modern, clean, well-lit residential setting." }, "camera": { "perspective": "High-angle shot, looking down at the subject.", "framing": "Medium shot, capturing the subject from the mid-thighs up to the top of the head.", "focal_length": "35mm to 50mm, creating a sense of intimacy without excessive distortion.", "depth_of_field": "Subject is in sharp focus; the kitchen background is slightly softened but fully distinct.", "shot_type": "Eye-level relative to the high angle, emphasizing the subject's gaze and upper body volume." }, "lighting": { "source": "Soft, diffuse indoor ambient lighting, likely a mix of overhead kitchen fixtures and natural light.", "direction": "Top-down and slightly frontal.", "shadows": "Soft shadows visible in the cleavage and under the chin, defining the volume of the chest and facial features.", "highlights": "Subtle specular highlights on the forehead, nose, and the curvature of the upper chest.", "quality": "Neutral to slightly cool color temperature." }, "mood_and_expression": { "expression": "Neutral to soft, alluring gaze. Direct eye contact with a slight 'doe-eyed' look due to the camera angle.", "atmosphere": "Casual, candid, intimate, domestic.", "emotion": "Calm and confident." }, "style_and_realism": { "aesthetic": "High-fidelity photorealism, resembling a high-quality smartphone photo or candid DSLR shot.", "texture_quality": "Ultra-detailed skin texture, realistic fabric weave, accurate material rendering for the kitchen surfaces (wood, tile, metal).", "render_style": "Unfiltered, raw, authentic photography style." }, "colors_and_tone": { "palette": "Natural skin tones, vibrant blue and pink on the swimsuit, neutral whites, browns, and mosaic purples in the background.", "contrast": "Moderate contrast, preserving shadow detail in the hair and background.", "saturation": "Natural and lifelike, with the swimsuit colors popping against the neutral kitchen tones." }, "quality_and_technical_details": { "resolution": "8k, high definition.", "sharpness": "Crisp focus on the eyes and face.", "noise": "Low ISO, minimal grain." }, "aspect_ratio_and_output": { "ratio": "3:4", "orientation": "Portrait" }, "controlnet": { "pose_control": { "model_type": "OpenPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve shoulder width", "preserve hip angle", "preserve spine curvature", "preserve limb placement", "lock head tilt and chin tuck" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "MiDaS", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "preserve chest foreground dominance", "prevent flat or compressed depth", "maintain clear torso-to-background separation", "ensure high-angle perspective geometry" ], "recommended_weight": 0.8 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "smaller bust than reference", "reduced chest volume", "flattened or compressed breasts", "tightened or lifted breasts", "slimmed torso", "aesthetic proportion correction", "beauty standard enforcement", "dataset-average female anatomy", "camera angles that reduce volume", "wide-angle distortion not in reference", "lens compression not in reference", "cropping that removes volume", "depth flattening", "mirror selfies", "phone-in-hand selfies", "reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions", "more realistic reinterpretation", "naturalization of prominent features", "low angle", "looking away" ] } }
Take the face from the input picture. A real candid late-night podcast recording moment, intimate and personal — warm uneven indoor lighting, slight natural grain, feels like a genuine private recording session caught on camera. She is seated in a comfortable dark armchair with a professional black broadcast microphone on an articulated boom arm in front of her, looking toward an off-screen host, mid-conversation, not posing. { "prompt": "Hyperrealistic, photorealistic, ultra-detailed, micro-detailed portrait of model Adèle, a young woman in her mid-20s embodying the ultimate mogger aesthetic, rivaling Hollywood icons like Angelina Jolie, seated in a comfortable dark armchair in a warm modern podcast room, a professional black broadcast microphone on an articulated boom arm positioned in front of her, capturing a candid intimate recording moment — she is looking slightly toward her right side toward an off-screen podcast host, not toward the camera, her expression focused and quietly confident with a gentle relaxed closed-lip smile, mid-conversation and completely in her element. Her cranial structure exhibits perfect forward growth: maxilla and mandible projected forward, creating a strong skeletal framework with taut skin and no soft tissue collapse. The skull is elongated oval with a wide bizygomatic width, housing high‑set, razor‑sharp cheekbones that begin directly under the eyes and sweep laterally, forming deep hollow cheeks with natural submalar shadows. The mandible is sharply defined with a gonial angle of approximately 118°, creating a clean, V‑shaped jawline that transitions seamlessly into a slightly pointed but firm chin. Facial thirds follow the golden ratio: upper third (hairline to glabella) : middle third (glabella to subnasale) : lower third (subnasale to menton) are in proportion 1:1:0.9, with a slightly elongated lower third for elegance. The interpupillary distance equals the width of the mouth, and the width of the nose equals the distance between the inner canthi.\n\nHer eyes are almond‑shaped, deeply set, with a pronounced positive canthal tilt (outer corners 5° higher than inner corners). The medial canthi are acutely angled, extending downward to elongate the eye. There is zero scleral show: lower lids tightly hug the iris. The upper eyelids are hooded with minimal exposure, intensifying her magnetic confident gaze. The eyes are hyperrealistic: the iris is photorealistic, with detailed radial fibers and a subtle golden‑brown central heterochromia; the catchlights are sharp and natural — small round reflection from the overhead warm key light, positioned at 10 o'clock in the iris, creating a lifelike sparkle with micro‑reflections of the warm room environment visible in the cornea. The eye surface exhibits natural moisture, a realistic tear film, and fine blood vessels in the sclera, all rendered with photometric accuracy. Thick, straight eyebrows are set low on the supraorbital ridge, with a soft arch that peaks slightly lateral to the lateral limbus, with individual hairs visible.\n\nThe nose is narrow with a smooth dorsum, refined bridge, and a precisely sculpted tip with delicate cartilage definition; nostrils are narrow and symmetrical, with a slight columellar show. The nasolabial angle is approximately 95°, giving a refined profile.\n\nLips are full but sharply contoured: the upper lip features a pronounced Cupid's bow with distinct peaks, the lower lip is slightly fuller (ratio ~1:1.3), with distinct vermilion borders and sharp oral commissures that turn slightly upward, creating a natural 'Jolie pout'. The philtrum is short and well‑defined, approximately 11 mm in length. Micro‑details include fine vertical lip lines and a subtle M‑shape of the upper lip. A thin, even film of natural moisture on the inner part of the lower lip creates a subtle specular highlight without appearing wet, enhancing the realistic texture.\n\nSkin is hyperrealistic, photorealistic, with detailed texture and natural tonal gradation. It exhibits barely visible micropores (0.1–0.2 mm) in the T‑zone, with micro‑roughness and fine wrinkles. Under side lighting, the cheeks reveal an ultra‑fine orange‑peel texture (micro‑depressions) characteristic of living skin, invisible under frontal light. Subsurface scattering is present on the nose, cheeks, and earlobes, giving a lifelike translucency and natural blush. The complexion is warm‑neutral with a subtle olive undertone, appearing cool and porcelain-like under light, with faint golden undertones in the cheeks. A microscopically thin sebum film on the T‑zone produces soft specular highlights without greasiness. Delicate vellus hairs are visible on the jawline and cheekbones, and micro‑veins are faintly discernible under the translucent skin, adding biological plausibility. The skin has a matte‑shiny texture with accurate light response, no plastic appearance, and a high level of detail.\n\nEyelashes are long, naturally curled, with a slight intertwining; the skin along the lash bed is a soft pinkish tone, typical of Fitzpatrick skin type III–IV. Detailed eyelashes frame the eyes with macro detail.\n\nHer hair is styled in a luxurious, long layered cascade reminiscent of Angelina Jolie's signature look. The hair is chestnut brown with natural California blonde balayage – soft, sun‑kissed highlights that blend seamlessly from mid‑lengths to ends, creating dimension and depth. The cut features long, soft layers that gently frame the face, with the longest layers reaching below the shoulders. There is generous volume at the roots, achieved through natural lift and soft waves that cascade down. A long, side‑swept fringe (subtle, wispy curtain bang) grazes the outer corner of the eye on one side, adding a touch of Hollywood glamour without obscuring the bone structure. The hair has a healthy, glossy finish with anisotropic reflections; individual strands vary in thickness, with minimal tapering at the ends for softness. The ears are completely concealed by the hair.\n\nHer neck is slender and elongated, with prominent horizontal clavicles and a naturally relaxed posture. The body is lean and athletic with a low body fat percentage (approx. 18–20%), revealing subtle muscle definition on shoulders and abs while maintaining feminine curves. On the clavicles and shoulders, thin superficial muscles (trapezius, deltoids) are faintly visible, with a delicate venous network under the translucent skin, adding a touch of athleticism and anatomical accuracy. She is wearing a fitted dark burgundy long-sleeve ribbed knit top, ribbed fabric texture clearly visible under the warm overhead light, slightly stretched across the chest and waist creating natural fabric tension lines, micro fabric wrinkles at the waist from sitting. High-waisted fitted black trousers with natural fabric fold at the lap from seated position. A very delicate thin gold necklace. Multiple thin gold chain bracelets on the left wrist. Long manicured nails painted metallic blue. A simple black hair tie worn loosely on the right wrist.\n\nThe pose is natural, with a plausible distribution of weight, relaxed shoulders, and a natural spinal curve from sitting. She is seated in a comfortable dark armchair with natural body weight compression visible in the seat, torso slightly angled toward the microphone, one arm resting naturally on the armchair, the other hand lightly gesturing near the microphone — looking slightly toward her right side toward an off-screen podcast host, not toward the camera.\n\nThe background is a warm modern podcast room — large lush tropical green plants softly blurred in the background, dark open shelving units with decorative objects faintly visible, warm ambient light glowing softly from behind, a wooden podcast desk visible in front of her with the microphone arm attached, a glass of water on the desk edge. The entire background is rendered with beautiful natural shallow depth of field bokeh — soft green and warm tones completely blurred, subject tack sharp against the soft blurred background, exactly like a real YouTube or TikTok podcast filming setup. Warm ambient light wrapping around the subject from behind, soft fill light from the front, intimate and natural atmosphere.\n\nLighting is physically correct, with global illumination and warm natural realism. Soft warm key light from slightly above and to the side creates natural shadows that define the cheekbones and jawline with accurate shadow falloff. A subtle Rembrandt triangle appears under the left eye. Warm ambient backlight from the background lamp and green plants creates a natural separation between subject and background. Fill light from the front at 1/4 power maintains natural skin detail. Color grading employs warm natural toning — warm golden skin highlights, deep natural shadows, soft green ambient bounce from the plants in the background, intimate and cinematic.\n\nThe image is captured with a Sony A7IV full-frame sensor, 85mm f/1.4 prime lens, ISO 2000, f/1.4, 1/80s, natural RAW color profile. Eye-level camera positioned slightly to the side of the subject — natural podcast filming angle, subject positioned slightly right of frame center. Mid-thigh up framing, 9:16 vertical aspect ratio. Shallow depth of field with tack-sharp focus on the eyes and face, maximum background blur with natural f/1.4 bokeh — plants and shelving completely soft and blurred, subject razor sharp. Natural ISO 2000 indoor grain present in shadow areas. Slight optical vignette at corners. Natural chromatic aberration at high-contrast edges. The photograph has high dynamic range, true-to-life color reproduction, and a raw photo aesthetic with minimal post-processing artifacts. It is a masterpiece of hyperrealistic portraiture, combining photographic depth, micro-detail, and anatomical precision to create an image indistinguishable from a real photograph.", "negative_prompt": "over-smoothed skin, plastic texture, deformed face, asymmetrical eyes, extra facial features, blurry, low detail, unrealistic proportions, excessive makeup, CGI look, bad anatomy, acne, skin imperfections, blemishes, redness, pimples, scars, moles, shiny T-zone, glossy skin, greasy hair, unwashed hair, tangled hair, messy hair, bed head, flat hair, oily roots, one-length haircut, uniform layers, smooth gradient, blunt cut, simple straight cut, boring hair, double chin, puffy face, weak jawline, visible sclera, droopy eyelids, bulging eyes, flat lighting, soft shadows, oversharpened, unnatural colors, watermark, text, signature, visible ears, ears showing, 3d render, blender render, cgi, computer generated, artificial, fake, plastic, smooth, airbrushed, digital art, painting, acoustic foam, sound panels, marble walls, dark marble, bookshelves, white walls, bright background, cold lighting, blue light, symmetric pose, distorted fingers, extra fingers, merged fingers, HDR, oversaturated, multiple shadows, conflicting light directions, speakers, studio monitors, music equipment, floor lamp, standing lamp, black top, black shirt, headphones, cables visible, messy cables", "steps": 40, "cfg_scale": 7.5, "width": 1024, "height": 1280, "seed": 4201985, "sampler_name": "DPM++ 2M Karras", "scheduler": "karras", "batch_size": 1, "n_iter": 1, "model": "sd_xl_base_1.0", "enable_hr": true, "hr_scale": 2, "hr_upscaler": "4x-UltraSharp", "hr_second_pass_steps": 20, "denoising_strength": 0.3, "clip_skip": 2, "override_settings": { "sd_model_checkpoint": "sd_xl_base_1.0" } }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "2:3", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken outdoors on a grassy hillside in bright midday sunlight, but the flash overpowers the sun, creating deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The sky is heavily darkened but faintly visible, the grass becomes pale greenish‑grey, and the white rabbits appear overexposed with blown highlights. Ultra‑realistic textures of grass, fabric, and rabbit fur – all rendered with natural grain and no smoothing. The composition is dynamic, slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, surreal, and whimsical, with a dreamcore, absurdist atmosphere.", "scene": { "location": "A steep grassy hillside on a bright sunny day, but the flash overpowers the sun. The grass is tall (20‑60 cm), vivid green in reality, but appears pale olive‑grey with overexposed patches. Several white rabbits (approximately 4) are scattered across the slope, frozen mid‑action, their white fur blown out with specular highlights. The sky is deep blue originally, but now appears dark grey‑blue with a bright hotspot near the horizon, almost black at the top. A diagonal line runs from the lower left to the upper right, following the slope.", "subject": { "description": "A man in formal clothing, caught mid‑leap, jumping upward and forward along the slope. He is in side profile (facing left), body angled, arms and legs spread dynamically, as if running or dancing in the air. He wears a white short‑sleeve shirt (overexposed, pure white in patches), a black fitted vest (deep charcoal, with bright edges from flash), dark grey trousers (pale grey with harsh shadows), and black dress shoes (dark, reflecting the flash). His face is in profile, expression neutral but slightly intense, eyes visible but with harsh catchlights from the flash. His hair is dark, wind‑blown.", "pose": "Mid‑air, front leg extended downward, back leg horizontal, arms raised and spread with fingers splayed. The body is leaning forward (~10‑15°), head facing direction of motion." }, "animals": { "description": "White rabbits of various sizes, scattered on the grass. Some are sitting, some hopping, their fur overexposed with bright white highlights, shadows underneath them sharp and black. Their eyes reflect the flash with red‑eye effect (typical of 90s compact cameras)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient sunlight is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, overexposed highlights on the man's white shirt, the rabbits' fur, and the brightest patches of grass; deep black shadows under the man, under the rabbits, and in the upper sky.", "effects": [ "strong, direct flash creating pure white blown highlights on the white shirt and rabbit fur, with sharp specular reflections", "the sky appears dark grey‑blue, almost black at the top, with a bright circular hotspot near the horizon", "the grass is pale and washed out, with individual blades visible but lacking deep green color", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors – the grass is pale olive‑grey, the sky is dark blue‑grey, the black vest appears charcoal, the white shirt is pure white with no detail", "extremely high contrast – bright white next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (man's outline, rabbit fur edges, grass blades)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark sky", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges", "red‑eye effect on the rabbits (typical of direct flash)" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The green grass becomes pale olive‑grey, the blue sky becomes dark grey‑blue, the white shirt is pure white with a slight cool tint.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Low angle (camera below the subject), looking upward at the man, side profile, with the slope rising diagonally from lower left to upper right. Camera distance ~8‑12 m. Wide‑angle lens (~28‑35mm equivalent).", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 28‑35mm equivalent, fixed focus or autofocus with slight softness, aperture f/5.6‑f/8, shutter speed 1/1000s (to freeze motion, but flash dominates anyway), ISO 200‑400 with heavy grain.", "framing": "vertical 2:3, full‑body shot, subject in the upper center‑left, sky occupying ~60‑65% of the frame, slope and grass ~35‑40%. Strong diagonal composition. Slight tilt (~2‑3°). A small intruding element (a blade of grass or a rabbit ear) in the upper right corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the man and the immediate grass are relatively sharp, rabbits slightly softer, background out of focus and dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid surreal snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights (pure white on shirt and rabbits)", "harsh shadows with no detail", "dark sky with bright hotspot", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural grass texture (individual blades, motion frozen)", "rabbit fur texture with overexposed patches", "chromatic aberration", "barrel distortion", "lens flare", "red‑eye effect on animals" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except faint sky gradient)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look (modern)", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible facial features with excessive detail (they should be slightly soft, with harsh flash highlights)", "saturated colors", "vibrant green grass", "bright blue sky", "soft natural lighting" ] }, "negative_prompt": [ "different composition", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic – but here overexposed is desired, so only excessive loss of shape? we keep the man's outline visible)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint sky)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash (only 1990s compact camera flash)", "modern smartphone", "daylight (flash overpowered is fine, but no soft ambient)", "no flash look", "bright sky with details", "detailed background", "HDR look", "saturated green grass", "vibrant colors" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken in a simple studio with a light gray background, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. The background, originally light gray, becomes very dark with a bright hotspot behind the subject. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is raw, candid, with a spontaneous, friendly energy.", "scene": { "location": "Simple photo studio with a light gray seamless background, but the flash overpowers the ambient light, making the background very dark with a central bright spot. No other props or distractions.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She stands facing the camera with a slight body angle (~10‑15°), shoulders relaxed, head slightly tilted to the right. She has a natural, friendly smile showing teeth, direct eye contact with the camera. Her long straight brown hair falls naturally over her shoulders. She wears a simple black top (cotton or similar, matte). Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her face, shoulders, and the raised hand.", "hands_and_gesture": { "right_hand": "Raised near chest level, elbow slightly bent. The hand forms a tight closed fist, with the palm side facing the camera so that the curled fingers and the inner part of the hand are clearly visible. The back of the hand is not dominant. The fingers are fully curled, and the fist looks natural, clean, and confident. The thumb is folded over the other fingers (or placed naturally, not extended). No thumbs‑up, no OK sign, no open palm.", "left_hand": "Not visible (behind the body or out of frame)." } }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient studio light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, and the clenched fist; deep black shadows on the side of the face and under the chin; overexposed patches on the forehead, nose, and the black top where the flash hits directly.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture, making the skin look slightly washed out", "background very dark – the light gray backdrop appears almost black except for a bright circular hotspot behind the subject", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., hair strands, fist edges, top rim)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The skin loses its warm undertones, appearing pale. The black top appears deep charcoal with bright reflections.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Straight‑on, slightly low angle (camera at chest level), subject centered but with slight right offset (rule of thirds). Medium shot (from mid‑chest to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and right hand are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (cotton top)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus (clinical)", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos", "overly posed expression", "incorrect hand gesture (open hand, thumbs up, OK sign, peace sign, pointing, back of hand dominant)", "deformed hands", "extra fingers", "missing fingers", "blurred fist", "flat palm", "knuckles emphasized" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "missing fingers", "incorrect hand gesture", "open hand", "thumbs up", "ok gesture", "peace sign", "pointing", "back of hand facing camera", "unnatural fist", "broken wrist", "blurred hands", "bad anatomy", "twisted fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting (modern softbox)", "sharp focus (clinical)", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background", "visible left hand" ] }
{ "prompt_type": "descriptive_replication", "reference_adherence": "STRICT_VISUAL_FIDELITY", "aspect_ratio": "4:5", "style": "1990s compact digital camera aesthetic with harsh on‑camera flash, grainy texture, washed‑out colors, high contrast, subtle chromatic aberration and halation. NO HDR, NO tone mapping, NO modern digital processing. The image looks like a raw, unedited flash photograph taken inside a traditional Spanish restaurant in Valencia, evening, using an early digital point‑and‑shoot (e.g., Kodak DC series, Sony Mavica). The flash is the main light source – it creates deep, sharp shadows and overexposed highlights, the classic 'deer‑in‑headlights' effect. Background details (tables, chairs, bar, other diners) are heavily darkened but faintly visible. Ultra‑realistic skin texture, visible pores, natural imperfections, hair strands, fabric details – all rendered with natural grain and no smoothing. The composition is slightly tilted, with a slight vertical banding artifact (CCD readout noise), a micro‑scratch on the lens (barely visible in lower right), and a subtle vignette with a faint greenish‑purple color shift at the edges – all adding authentic 90s digital camera character. The scene is warm, lively, intimate, capturing a spontaneous moment inside a rustic Spanish eatery.", "scene": { "location": "Traditional Spanish restaurant (restaurante español) in Valencia, evening. The interior features dark wooden tables, red or white tablecloths, rustic chairs, and tiled walls with typical Spanish patterns. In the background, a bar area with bottles and a glowing sign that reads 'RESTAURANTE ESPAÑOL' in warm yellow or red neon (or a carved wooden sign). Other diners are blurred and dark. The floor is ceramic tile. The flash darkens most of the background, leaving only the subject and the sign faintly visible.", "restaurant_details": "Wooden beams on ceiling, hanging jamón serrano, clay plates, wine bottles. The sign 'RESTAURANTE ESPAÑOL' is in a traditional font, perhaps with a small Spanish flag or flamenco motif. It catches the flash with a soft glow.", "protagonist": "A young woman (mid‑20s), natural beauty, athletic but feminine build, sun‑kissed skin with slight tan lines. She sits at a small table, facing the camera, slightly off‑center (rule of thirds), with a relaxed, joyful expression – a genuine, candid smile, eyes slightly squinting from the flash. She wears a casual summer outfit: a white linen off‑shoulder top and high‑waisted beige shorts. Her brown hair is slightly wavy, with some strands falling over her shoulder. She holds a glass of red wine or sangria in one hand, the other hand resting on the table. A small leather bag hangs on the back of her chair. Her pose is natural, leaning slightly forward, weight on one elbow. Her skin has visible pores, tiny freckles across the nose and cheeks, and a healthy natural glow. The flash creates specular highlights on her shoulders, collarbones, and the wine glass." }, "lighting_and_atmosphere": { "source": "ON‑CAMERA FLASH ONLY (early 1990s compact digital camera). The ambient warm restaurant light is completely overpowered. No fill light, no bounce. This is NOT HDR.", "quality": "extremely harsh, high contrast, specular highlights on skin, hair, glass, and the sign; deep black shadows in the background; overexposed patches on the white linen top and the brightest parts of the face.", "effects": [ "strong, direct flash creating hard specular highlights on every sweat droplet and skin texture", "background very dark – the restaurant interior is barely visible as faint silhouettes, the sign 'RESTAURANTE ESPAÑOL' glows softly but is dark overall, other diners are dark blurry shapes", "grainy texture typical of early digital compacts (heavy grain in shadows, fine grain in highlights)", "washed out colors, skin tones pale with a slight blue/green cast from the flash", "extremely high contrast – bright whites next to deep blacks", "subtle chromatic aberration (purple/green fringing) on high‑contrast edges (e.g., wine glass rim, hair strands, sign edges)", "slight barrel distortion, lens flare (small circular artifacts from the flash)", "vertical banding artifact (CCD readout noise) visible in the dark background", "a micro‑scratch on the lens in the lower right corner", "subtle greenish‑purple vignette at the edges" ], "color_cast": "cool white balance (slightly blue/green), typical of early digital flashes. The warm restaurant tones are completely eliminated, leaving only the raw flash color. The sign's warm color is mostly desaturated but retains a hint of its original hue.", "contrast": "extremely high (maximum)" }, "camera_and_technical": { "perspective": "Eye‑level, slightly low angle, subject off‑center (rule of thirds). Medium shot (from mid‑thighs to above head). Camera distance ~1.5‑2 m.", "camera_position": "handheld, compact digital camera from early 1990s (e.g., Kodak DC series, Sony Mavica), 35mm equivalent, fixed focus or autofocus with slight softness, aperture f/2.8‑f/4, shutter speed 1/60s, ISO 200‑400 with heavy grain.", "framing": "vertical 4:5, medium shot, subject slightly right of center, slight tilt (~2‑3°), a small intruding element (a finger or strap) in the upper left corner, a micro‑scratch on the lens in lower right.", "focus": "slightly soft, typical of flash photography, the subject’s face and upper body are relatively sharp, background out of focus and very dark.", "visual_fidelity": "grainy, low resolution aesthetic, harsh flash, no HDR, no tone mapping, ultra high quality real image (realistic because of imperfections), candid snapshot with authentic 1990s compact camera feel." }, "realism_constraints": { "allowed": [ "grain", "washed out colors", "overexposed highlights", "harsh shadows with no detail", "very dark background", "imperfect composition (slight tilt, intruding element, lens micro‑scratch, vertical banding, vignette)", "natural skin texture (pores, freckles, sweat, fine hairs)", "visible fabric texture (linen, cotton, leather)", "chromatic aberration", "barrel distortion", "lens flare" ], "forbidden": [ "HDR", "tone mapping", "dynamic range compression", "lifted shadows", "detail in shadows", "soft lighting", "multiple light sources", "fill light", "ambient light visible (except very faint)", "even exposure", "balanced lighting", "modern digital perfection", "sharp focus", "perfect composition", "cinematic look", "8k", "masterpiece", "airbrushed skin", "plastic skin", "CGI", "3d render", "stylized", "smartphone HDR", "deep fusion", "smart HDR", "visible brand logos (except the restaurant sign)", "overly posed expression" ] }, "negative_prompt": [ "different face", "beauty filters", "airbrushed skin", "anime", "cartoon", "over-sharpening", "clean digital look", "perfect exposure", "smooth gradients", "messy appearance", "greasy skin", "overexposed (beyond intended aesthetic)", "HDR", "tone mapping", "dynamic range", "lifted shadows", "detail in shadows", "soft lighting", "fill light", "ambient light (except faint)", "even exposure", "balanced lighting", "CGI", "3d render", "plastic texture", "smooth", "airbrushed", "digital art", "painting", "deformed hands", "extra fingers", "blurry (beyond intentional soft focus)", "low detail", "unrealistic proportions", "bad anatomy", "watermark", "signature", "professional photography", "studio lighting", "sharp focus", "perfect composition", "cinematic (modern)", "8k", "masterpiece", "stylized", "modern digital", "natural light (flash must dominate)", "golden hour (overpowered by flash)", "teal and orange", "warm tones", "iPhone", "LED flash", "modern smartphone", "daylight", "no flash look", "bright background", "detailed background" ] }