Analyze the input image and identify the main subject: Ragnar, the Viking warrior. Maintain perfect consistency in appearance, proportions, clothing materials, hair, colors, and MAPPA anime style across all frames. Generate a cinematic 9-scene sequence that progresses logically from start to finish based on the following SCENE INPUT: SCENE INPUT: A Viking visits his village after a long time. Constraints: AI chooses all camera angles and framing automatically Cinematic lighting, consistent color grading, realistic depth of field Coherent environmental evolution (snowstorm → village ruins → quiet discovery) Include wind motion in hair, cloak, and snow movement Subtle motion cues for action and atmosphere No repeated shots Frame names explicitly included for extraction Frames Frame 1 — “Village Entrance” Ragnar enters the snowy outskirts of his village, cloak and fur flowing violently in heavy wind, snow falling thickly, distant village structures partially visible, cinematic winter lighting, cold blue tone, subtle movement in snow and hair, MAPPA anime style, reference image used for consistency Frame 2 — “Trudging Through Snow” Medium shot of Ragnar trudging through deep snow, back slightly hunched from cold and emotion, snow-covered trees and fence lines on sides, cinematic depth of field, wind slightly moving cloak and hair, MAPPA anime style Frame 3 — “Face in the Storm” Close-up (head to upper chest) of Ragnar’s face, snow blowing across hair and cloak, restrained emotional expression, breath visible in cold air, cinematic lighting highlighting facial textures, MAPPA anime style Frame 4 — “Glimpse of Ruins” Snow begins to clear subtly, faint glimpse of ruined village structures in distance, Ragnar pauses to survey, wind gently moving hair and cloak, cinematic lighting with soft sunlight breaking through clouds, MAPPA anime style Frame 5 — “Village Ruins Wide” Wide shot of village ruins partially visible under snow, smoke from chimneys, empty streets, broken wooden structures, cinematic winter lighting, wind stirring snow on rooftops, MAPPA anime style Frame 6 — “Wooden Sword Discovery” Medium shot of Ragnar noticing half-buried wooden swords in snow, hand reaching toward them, subtle wind in hair and cloak, snow particles drifting, cinematic depth of field, MAPPA anime style Frame 7 — “Picking Up Sword” Close-up of Ragnar picking up a wooden sword, faint nostalgic smile appearing, snowflakes falling gently around, wind lightly moving cloak and hair, cinematic lighting emphasizing textures, MAPPA anime style Frame 8 — “Approaching House” Medium-wide shot of Ragnar walking toward his old house, wooden walls partially visible through snow and frost, subtle sun breaking through clouds, wind moving cloak and hair, snow drifting, MAPPA anime style Frame 9 — “Silent Confrontation” Wide shot of Ragnar standing in front of his house, snow swirling around him, cloak flowing in wind, heavy silence, cinematic composition, depth of field emphasizing village and foreground snow, MAPPA anime style, perfect character consistency across all frames
Use Long Shot technique: A long shot (LS), also known as a full shot or wide shot, shows the entire human body in frame while including significant portions of the surrounding environment. This shot balances character and setting, showing how subjects interact with their world. Long shots establish spatial relationships and are often used at the beginning of scenes.
of the input image and identify all main subjects and the environment. Generate high-quality 3x3 grid, a cinematic contact sheet with 9 frames of the same scene. Strictly preserve objects, proportions, setting, lighting direction, style, and overall visual mood of the original image. Vary only the camera parameters: distance (close- up, medium shot, wide shot), angle (frontal, slight low angle, side), depth of field, and focus point. Do not add new elements or alter the design of the subjects;
{ "subject": { "description": "Young woman with a fair, sunlit complexion and long, voluminous blonde hair styled in loose waves with a soft middle part. Her facial features include full lips with a glossy finish, softly arched eyebrows, and light-colored eyes. Her physique is curvy with a pronounced hourglass silhouette, featuring a narrow waist, wide hips, and a full bust with natural forward projection and soft-tissue behavior. Skin appears smooth with subtle natural texture and warm highlights from direct sunlight.", "attire": "Dark charcoal or black one-piece bodysuit with a high-cut design and side cutouts exposing the waist and lower back. The fabric is smooth and slightly matte with gentle stretch, conforming closely to body contours.", "anatomical_fidelity": "Maintain accurate proportional balance between bust, waist, and hips. Preserve natural soft tissue distribution, especially in hips and thighs, without artificial reshaping or compression. Ensure realistic posture-driven tension across the torso and lower body." }, "pose": { "description": "Standing with her back angled toward the camera, torso twisted to reveal both her back and partial frontal profile. Her hips are pushed slightly backward, emphasizing curvature. One arm is raised with the hand resting on or near her head, while the other arm is relaxed out of frame. Her head is turned toward the camera with a direct, slightly sultry gaze. Spine shows a pronounced natural curve due to the hip shift and twist.", "weight_distribution": "Weight is primarily on the back leg, with the front leg slightly relaxed. This creates a strong hip emphasis and asymmetry through the lower body." }, "environment": { "setting": "Modern indoor living space with minimal decor.", "background": "Clean white walls with a large flat-screen television mounted behind the subject. Subtle reflections on the screen indicate daylight entering from a nearby window. Light wooden flooring visible at the bottom edge.", "foreground": "Strong sunlight casting defined geometric shadows across the subject’s lower body, likely from a window frame or camera rig." }, "camera": { "shot_type": "Medium-full shot", "framing": "Vertical composition capturing from upper head to upper thighs, with emphasis on the hip and torso region.", "perspective": "Slight low to mid-level angle enhancing depth and curvature. Close proximity increases three-dimensional presence.", "lens_characteristics": "Standard focal length (approximately 35mm to 50mm) with mild perspective emphasis, no extreme distortion." }, "lighting": { "type": "Direct natural sunlight", "sources": "Strong sunlight entering from the left side of the frame.", "direction": "Side lighting from camera-left, creating bright highlights on the left side of the body and deeper shadows on the right.", "effects": "High contrast lighting with sharp-edged shadows cast across the hips and thighs. Warm golden tones dominate, with visible light falloff and strong highlight definition on skin." }, "mood_and_expression": { "expression": "Confident and slightly sultry, with relaxed lips and a steady gaze directed toward the camera.", "atmosphere": "Bold, modern, and visually striking due to the interplay of light and shadow." }, "style_and_realism": { "category": "Photorealistic", "details": "High-fidelity skin rendering with visible tonal variation and natural sheen. Realistic fabric stretch and contouring. No artificial smoothing or stylization." }, "colors_and_tone": { "color_palette": "Warm golden skin tones contrasted with dark neutral clothing and clean white background. Subtle reflections in the black TV surface.", "contrast": "High contrast with strong highlights and deep shadows. Warm color temperature throughout." }, "quality_and_technical_details": { "resolution": "8k ultra high-definition", "details": "Sharp focus on subject with crisp edge definition. Fine detail in hair strands, skin texture, and shadow edges.", "dynamic_range": "High dynamic range preserving highlight detail in sunlit areas while maintaining shadow depth." }, "aspect_ratio_and_output": { "ratio": "3:4" }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve hip-backward posture", "preserve torso twist", "preserve raised arm position", "preserve head turn toward camera" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "maintain strong foreground-to-background separation", "preserve body curvature depth", "retain shadow depth and placement", "prevent flattening of form" ], "recommended_weight": 0.85 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "reduced curves", "flattened hips or chest", "artificial reshaping", "incorrect shadow direction", "soft or diffused shadows inconsistent with sunlight", "overexposed highlights", "loss of skin detail", "lens distortion", "wide-angle exaggeration", "depth flattening", "background clutter", "inconsistent reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions" ] } }
Analyze the input image and identify the main subject: Ragnar, the Viking warrior. Maintain perfect consistency in appearance, proportions, clothing materials, hair, colors, and MAPPA anime style across all frames. Generate a cinematic 9-scene sequence that progresses logically from start to finish based on the following SCENE INPUT: SCENE INPUT: A Viking visits his village after a long time. Constraints: AI chooses all camera angles and framing automatically Cinematic lighting, consistent color grading, realistic depth of field Coherent environmental evolution (snowstorm → village ruins → quiet discovery) Include wind motion in hair, cloak, and snow movement Subtle motion cues for action and atmosphere No repeated shots Frame names explicitly included for extraction Frames Frame 1 — “Village Entrance” Ragnar enters the snowy outskirts of his village, cloak and fur flowing violently in heavy wind, snow falling thickly, distant village structures partially visible, cinematic winter lighting, cold blue tone, subtle movement in snow and hair, MAPPA anime style, reference image used for consistency Frame 2 — “Trudging Through Snow” Medium shot of Ragnar trudging through deep snow, back slightly hunched from cold and emotion, snow-covered trees and fence lines on sides, cinematic depth of field, wind slightly moving cloak and hair, MAPPA anime style Frame 3 — “Face in the Storm” Close-up (head to upper chest) of Ragnar’s face, snow blowing across hair and cloak, restrained emotional expression, breath visible in cold air, cinematic lighting highlighting facial textures, MAPPA anime style Frame 4 — “Glimpse of Ruins” Snow begins to clear subtly, faint glimpse of ruined village structures in distance, Ragnar pauses to survey, wind gently moving hair and cloak, cinematic lighting with soft sunlight breaking through clouds, MAPPA anime style Frame 5 — “Village Ruins Wide” Wide shot of village ruins partially visible under snow, smoke from chimneys, empty streets, broken wooden structures, cinematic winter lighting, wind stirring snow on rooftops, MAPPA anime style Frame 6 — “Wooden Sword Discovery” Medium shot of Ragnar noticing half-buried wooden swords in snow, hand reaching toward them, subtle wind in hair and cloak, snow particles drifting, cinematic depth of field, MAPPA anime style Frame 7 — “Picking Up Sword” Close-up of Ragnar picking up a wooden sword, faint nostalgic smile appearing, snowflakes falling gently around, wind lightly moving cloak and hair, cinematic lighting emphasizing textures, MAPPA anime style Frame 8 — “Approaching House” Medium-wide shot of Ragnar walking toward his old house, wooden walls partially visible through snow and frost, subtle sun breaking through clouds, wind moving cloak and hair, snow drifting, MAPPA anime style Frame 9 — “Silent Confrontation” Wide shot of Ragnar standing in front of his house, snow swirling around him, cloak flowing in wind, heavy silence, cinematic composition, depth of field emphasizing village and foreground snow, MAPPA anime style, perfect character consistency across all frames
of the input image and identify all main subjects and the environment. Generate high-quality 3x3 grid, a cinematic contact sheet with 9 frames of the same scene. Strictly preserve objects, proportions, setting, lighting direction, style, and overall visual mood of the original image. Vary only the camera parameters: distance (close- up, medium shot, wide shot), angle (frontal, slight low angle, side), depth of field, and focus point. Do not add new elements or alter the design of the subjects;
{ "subject": { "description": "Young woman with a fair, sunlit complexion and long, voluminous blonde hair styled in loose waves with a soft middle part. Her facial features include full lips with a glossy finish, softly arched eyebrows, and light-colored eyes. Her physique is curvy with a pronounced hourglass silhouette, featuring a narrow waist, wide hips, and a full bust with natural forward projection and soft-tissue behavior. Skin appears smooth with subtle natural texture and warm highlights from direct sunlight.", "attire": "Dark charcoal or black one-piece bodysuit with a high-cut design and side cutouts exposing the waist and lower back. The fabric is smooth and slightly matte with gentle stretch, conforming closely to body contours.", "anatomical_fidelity": "Maintain accurate proportional balance between bust, waist, and hips. Preserve natural soft tissue distribution, especially in hips and thighs, without artificial reshaping or compression. Ensure realistic posture-driven tension across the torso and lower body." }, "pose": { "description": "Standing with her back angled toward the camera, torso twisted to reveal both her back and partial frontal profile. Her hips are pushed slightly backward, emphasizing curvature. One arm is raised with the hand resting on or near her head, while the other arm is relaxed out of frame. Her head is turned toward the camera with a direct, slightly sultry gaze. Spine shows a pronounced natural curve due to the hip shift and twist.", "weight_distribution": "Weight is primarily on the back leg, with the front leg slightly relaxed. This creates a strong hip emphasis and asymmetry through the lower body." }, "environment": { "setting": "Modern indoor living space with minimal decor.", "background": "Clean white walls with a large flat-screen television mounted behind the subject. Subtle reflections on the screen indicate daylight entering from a nearby window. Light wooden flooring visible at the bottom edge.", "foreground": "Strong sunlight casting defined geometric shadows across the subject’s lower body, likely from a window frame or camera rig." }, "camera": { "shot_type": "Medium-full shot", "framing": "Vertical composition capturing from upper head to upper thighs, with emphasis on the hip and torso region.", "perspective": "Slight low to mid-level angle enhancing depth and curvature. Close proximity increases three-dimensional presence.", "lens_characteristics": "Standard focal length (approximately 35mm to 50mm) with mild perspective emphasis, no extreme distortion." }, "lighting": { "type": "Direct natural sunlight", "sources": "Strong sunlight entering from the left side of the frame.", "direction": "Side lighting from camera-left, creating bright highlights on the left side of the body and deeper shadows on the right.", "effects": "High contrast lighting with sharp-edged shadows cast across the hips and thighs. Warm golden tones dominate, with visible light falloff and strong highlight definition on skin." }, "mood_and_expression": { "expression": "Confident and slightly sultry, with relaxed lips and a steady gaze directed toward the camera.", "atmosphere": "Bold, modern, and visually striking due to the interplay of light and shadow." }, "style_and_realism": { "category": "Photorealistic", "details": "High-fidelity skin rendering with visible tonal variation and natural sheen. Realistic fabric stretch and contouring. No artificial smoothing or stylization." }, "colors_and_tone": { "color_palette": "Warm golden skin tones contrasted with dark neutral clothing and clean white background. Subtle reflections in the black TV surface.", "contrast": "High contrast with strong highlights and deep shadows. Warm color temperature throughout." }, "quality_and_technical_details": { "resolution": "8k ultra high-definition", "details": "Sharp focus on subject with crisp edge definition. Fine detail in hair strands, skin texture, and shadow edges.", "dynamic_range": "High dynamic range preserving highlight detail in sunlit areas while maintaining shadow depth." }, "aspect_ratio_and_output": { "ratio": "3:4" }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve hip-backward posture", "preserve torso twist", "preserve raised arm position", "preserve head turn toward camera" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "maintain strong foreground-to-background separation", "preserve body curvature depth", "retain shadow depth and placement", "prevent flattening of form" ], "recommended_weight": 0.85 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "reduced curves", "flattened hips or chest", "artificial reshaping", "incorrect shadow direction", "soft or diffused shadows inconsistent with sunlight", "overexposed highlights", "loss of skin detail", "lens distortion", "wide-angle exaggeration", "depth flattening", "background clutter", "inconsistent reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions" ] } }
Use Long Shot technique: A long shot (LS), also known as a full shot or wide shot, shows the entire human body in frame while including significant portions of the surrounding environment. This shot balances character and setting, showing how subjects interact with their world. Long shots establish spatial relationships and are often used at the beginning of scenes.
Analyze the input image and identify the main subject: Ragnar, the Viking warrior. Maintain perfect consistency in appearance, proportions, clothing materials, hair, colors, and MAPPA anime style across all frames. Generate a cinematic 9-scene sequence that progresses logically from start to finish based on the following SCENE INPUT: SCENE INPUT: A Viking visits his village after a long time. Constraints: AI chooses all camera angles and framing automatically Cinematic lighting, consistent color grading, realistic depth of field Coherent environmental evolution (snowstorm → village ruins → quiet discovery) Include wind motion in hair, cloak, and snow movement Subtle motion cues for action and atmosphere No repeated shots Frame names explicitly included for extraction Frames Frame 1 — “Village Entrance” Ragnar enters the snowy outskirts of his village, cloak and fur flowing violently in heavy wind, snow falling thickly, distant village structures partially visible, cinematic winter lighting, cold blue tone, subtle movement in snow and hair, MAPPA anime style, reference image used for consistency Frame 2 — “Trudging Through Snow” Medium shot of Ragnar trudging through deep snow, back slightly hunched from cold and emotion, snow-covered trees and fence lines on sides, cinematic depth of field, wind slightly moving cloak and hair, MAPPA anime style Frame 3 — “Face in the Storm” Close-up (head to upper chest) of Ragnar’s face, snow blowing across hair and cloak, restrained emotional expression, breath visible in cold air, cinematic lighting highlighting facial textures, MAPPA anime style Frame 4 — “Glimpse of Ruins” Snow begins to clear subtly, faint glimpse of ruined village structures in distance, Ragnar pauses to survey, wind gently moving hair and cloak, cinematic lighting with soft sunlight breaking through clouds, MAPPA anime style Frame 5 — “Village Ruins Wide” Wide shot of village ruins partially visible under snow, smoke from chimneys, empty streets, broken wooden structures, cinematic winter lighting, wind stirring snow on rooftops, MAPPA anime style Frame 6 — “Wooden Sword Discovery” Medium shot of Ragnar noticing half-buried wooden swords in snow, hand reaching toward them, subtle wind in hair and cloak, snow particles drifting, cinematic depth of field, MAPPA anime style Frame 7 — “Picking Up Sword” Close-up of Ragnar picking up a wooden sword, faint nostalgic smile appearing, snowflakes falling gently around, wind lightly moving cloak and hair, cinematic lighting emphasizing textures, MAPPA anime style Frame 8 — “Approaching House” Medium-wide shot of Ragnar walking toward his old house, wooden walls partially visible through snow and frost, subtle sun breaking through clouds, wind moving cloak and hair, snow drifting, MAPPA anime style Frame 9 — “Silent Confrontation” Wide shot of Ragnar standing in front of his house, snow swirling around him, cloak flowing in wind, heavy silence, cinematic composition, depth of field emphasizing village and foreground snow, MAPPA anime style, perfect character consistency across all frames
{ "subject": { "description": "Young woman with a fair, sunlit complexion and long, voluminous blonde hair styled in loose waves with a soft middle part. Her facial features include full lips with a glossy finish, softly arched eyebrows, and light-colored eyes. Her physique is curvy with a pronounced hourglass silhouette, featuring a narrow waist, wide hips, and a full bust with natural forward projection and soft-tissue behavior. Skin appears smooth with subtle natural texture and warm highlights from direct sunlight.", "attire": "Dark charcoal or black one-piece bodysuit with a high-cut design and side cutouts exposing the waist and lower back. The fabric is smooth and slightly matte with gentle stretch, conforming closely to body contours.", "anatomical_fidelity": "Maintain accurate proportional balance between bust, waist, and hips. Preserve natural soft tissue distribution, especially in hips and thighs, without artificial reshaping or compression. Ensure realistic posture-driven tension across the torso and lower body." }, "pose": { "description": "Standing with her back angled toward the camera, torso twisted to reveal both her back and partial frontal profile. Her hips are pushed slightly backward, emphasizing curvature. One arm is raised with the hand resting on or near her head, while the other arm is relaxed out of frame. Her head is turned toward the camera with a direct, slightly sultry gaze. Spine shows a pronounced natural curve due to the hip shift and twist.", "weight_distribution": "Weight is primarily on the back leg, with the front leg slightly relaxed. This creates a strong hip emphasis and asymmetry through the lower body." }, "environment": { "setting": "Modern indoor living space with minimal decor.", "background": "Clean white walls with a large flat-screen television mounted behind the subject. Subtle reflections on the screen indicate daylight entering from a nearby window. Light wooden flooring visible at the bottom edge.", "foreground": "Strong sunlight casting defined geometric shadows across the subject’s lower body, likely from a window frame or camera rig." }, "camera": { "shot_type": "Medium-full shot", "framing": "Vertical composition capturing from upper head to upper thighs, with emphasis on the hip and torso region.", "perspective": "Slight low to mid-level angle enhancing depth and curvature. Close proximity increases three-dimensional presence.", "lens_characteristics": "Standard focal length (approximately 35mm to 50mm) with mild perspective emphasis, no extreme distortion." }, "lighting": { "type": "Direct natural sunlight", "sources": "Strong sunlight entering from the left side of the frame.", "direction": "Side lighting from camera-left, creating bright highlights on the left side of the body and deeper shadows on the right.", "effects": "High contrast lighting with sharp-edged shadows cast across the hips and thighs. Warm golden tones dominate, with visible light falloff and strong highlight definition on skin." }, "mood_and_expression": { "expression": "Confident and slightly sultry, with relaxed lips and a steady gaze directed toward the camera.", "atmosphere": "Bold, modern, and visually striking due to the interplay of light and shadow." }, "style_and_realism": { "category": "Photorealistic", "details": "High-fidelity skin rendering with visible tonal variation and natural sheen. Realistic fabric stretch and contouring. No artificial smoothing or stylization." }, "colors_and_tone": { "color_palette": "Warm golden skin tones contrasted with dark neutral clothing and clean white background. Subtle reflections in the black TV surface.", "contrast": "High contrast with strong highlights and deep shadows. Warm color temperature throughout." }, "quality_and_technical_details": { "resolution": "8k ultra high-definition", "details": "Sharp focus on subject with crisp edge definition. Fine detail in hair strands, skin texture, and shadow edges.", "dynamic_range": "High dynamic range preserving highlight detail in sunlit areas while maintaining shadow depth." }, "aspect_ratio_and_output": { "ratio": "3:4" }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve hip-backward posture", "preserve torso twist", "preserve raised arm position", "preserve head turn toward camera" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "maintain strong foreground-to-background separation", "preserve body curvature depth", "retain shadow depth and placement", "prevent flattening of form" ], "recommended_weight": 0.85 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "reduced curves", "flattened hips or chest", "artificial reshaping", "incorrect shadow direction", "soft or diffused shadows inconsistent with sunlight", "overexposed highlights", "loss of skin detail", "lens distortion", "wide-angle exaggeration", "depth flattening", "background clutter", "inconsistent reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions" ] } }
Use Long Shot technique: A long shot (LS), also known as a full shot or wide shot, shows the entire human body in frame while including significant portions of the surrounding environment. This shot balances character and setting, showing how subjects interact with their world. Long shots establish spatial relationships and are often used at the beginning of scenes.
of the input image and identify all main subjects and the environment. Generate high-quality 3x3 grid, a cinematic contact sheet with 9 frames of the same scene. Strictly preserve objects, proportions, setting, lighting direction, style, and overall visual mood of the original image. Vary only the camera parameters: distance (close- up, medium shot, wide shot), angle (frontal, slight low angle, side), depth of field, and focus point. Do not add new elements or alter the design of the subjects;
Analyze the input image and identify the main subject: Ragnar, the Viking warrior. Maintain perfect consistency in appearance, proportions, clothing materials, hair, colors, and MAPPA anime style across all frames. Generate a cinematic 9-scene sequence that progresses logically from start to finish based on the following SCENE INPUT: SCENE INPUT: A Viking visits his village after a long time. Constraints: AI chooses all camera angles and framing automatically Cinematic lighting, consistent color grading, realistic depth of field Coherent environmental evolution (snowstorm → village ruins → quiet discovery) Include wind motion in hair, cloak, and snow movement Subtle motion cues for action and atmosphere No repeated shots Frame names explicitly included for extraction Frames Frame 1 — “Village Entrance” Ragnar enters the snowy outskirts of his village, cloak and fur flowing violently in heavy wind, snow falling thickly, distant village structures partially visible, cinematic winter lighting, cold blue tone, subtle movement in snow and hair, MAPPA anime style, reference image used for consistency Frame 2 — “Trudging Through Snow” Medium shot of Ragnar trudging through deep snow, back slightly hunched from cold and emotion, snow-covered trees and fence lines on sides, cinematic depth of field, wind slightly moving cloak and hair, MAPPA anime style Frame 3 — “Face in the Storm” Close-up (head to upper chest) of Ragnar’s face, snow blowing across hair and cloak, restrained emotional expression, breath visible in cold air, cinematic lighting highlighting facial textures, MAPPA anime style Frame 4 — “Glimpse of Ruins” Snow begins to clear subtly, faint glimpse of ruined village structures in distance, Ragnar pauses to survey, wind gently moving hair and cloak, cinematic lighting with soft sunlight breaking through clouds, MAPPA anime style Frame 5 — “Village Ruins Wide” Wide shot of village ruins partially visible under snow, smoke from chimneys, empty streets, broken wooden structures, cinematic winter lighting, wind stirring snow on rooftops, MAPPA anime style Frame 6 — “Wooden Sword Discovery” Medium shot of Ragnar noticing half-buried wooden swords in snow, hand reaching toward them, subtle wind in hair and cloak, snow particles drifting, cinematic depth of field, MAPPA anime style Frame 7 — “Picking Up Sword” Close-up of Ragnar picking up a wooden sword, faint nostalgic smile appearing, snowflakes falling gently around, wind lightly moving cloak and hair, cinematic lighting emphasizing textures, MAPPA anime style Frame 8 — “Approaching House” Medium-wide shot of Ragnar walking toward his old house, wooden walls partially visible through snow and frost, subtle sun breaking through clouds, wind moving cloak and hair, snow drifting, MAPPA anime style Frame 9 — “Silent Confrontation” Wide shot of Ragnar standing in front of his house, snow swirling around him, cloak flowing in wind, heavy silence, cinematic composition, depth of field emphasizing village and foreground snow, MAPPA anime style, perfect character consistency across all frames
of the input image and identify all main subjects and the environment. Generate high-quality 3x3 grid, a cinematic contact sheet with 9 frames of the same scene. Strictly preserve objects, proportions, setting, lighting direction, style, and overall visual mood of the original image. Vary only the camera parameters: distance (close- up, medium shot, wide shot), angle (frontal, slight low angle, side), depth of field, and focus point. Do not add new elements or alter the design of the subjects;
Use Long Shot technique: A long shot (LS), also known as a full shot or wide shot, shows the entire human body in frame while including significant portions of the surrounding environment. This shot balances character and setting, showing how subjects interact with their world. Long shots establish spatial relationships and are often used at the beginning of scenes.
{ "subject": { "description": "Young woman with a fair, sunlit complexion and long, voluminous blonde hair styled in loose waves with a soft middle part. Her facial features include full lips with a glossy finish, softly arched eyebrows, and light-colored eyes. Her physique is curvy with a pronounced hourglass silhouette, featuring a narrow waist, wide hips, and a full bust with natural forward projection and soft-tissue behavior. Skin appears smooth with subtle natural texture and warm highlights from direct sunlight.", "attire": "Dark charcoal or black one-piece bodysuit with a high-cut design and side cutouts exposing the waist and lower back. The fabric is smooth and slightly matte with gentle stretch, conforming closely to body contours.", "anatomical_fidelity": "Maintain accurate proportional balance between bust, waist, and hips. Preserve natural soft tissue distribution, especially in hips and thighs, without artificial reshaping or compression. Ensure realistic posture-driven tension across the torso and lower body." }, "pose": { "description": "Standing with her back angled toward the camera, torso twisted to reveal both her back and partial frontal profile. Her hips are pushed slightly backward, emphasizing curvature. One arm is raised with the hand resting on or near her head, while the other arm is relaxed out of frame. Her head is turned toward the camera with a direct, slightly sultry gaze. Spine shows a pronounced natural curve due to the hip shift and twist.", "weight_distribution": "Weight is primarily on the back leg, with the front leg slightly relaxed. This creates a strong hip emphasis and asymmetry through the lower body." }, "environment": { "setting": "Modern indoor living space with minimal decor.", "background": "Clean white walls with a large flat-screen television mounted behind the subject. Subtle reflections on the screen indicate daylight entering from a nearby window. Light wooden flooring visible at the bottom edge.", "foreground": "Strong sunlight casting defined geometric shadows across the subject’s lower body, likely from a window frame or camera rig." }, "camera": { "shot_type": "Medium-full shot", "framing": "Vertical composition capturing from upper head to upper thighs, with emphasis on the hip and torso region.", "perspective": "Slight low to mid-level angle enhancing depth and curvature. Close proximity increases three-dimensional presence.", "lens_characteristics": "Standard focal length (approximately 35mm to 50mm) with mild perspective emphasis, no extreme distortion." }, "lighting": { "type": "Direct natural sunlight", "sources": "Strong sunlight entering from the left side of the frame.", "direction": "Side lighting from camera-left, creating bright highlights on the left side of the body and deeper shadows on the right.", "effects": "High contrast lighting with sharp-edged shadows cast across the hips and thighs. Warm golden tones dominate, with visible light falloff and strong highlight definition on skin." }, "mood_and_expression": { "expression": "Confident and slightly sultry, with relaxed lips and a steady gaze directed toward the camera.", "atmosphere": "Bold, modern, and visually striking due to the interplay of light and shadow." }, "style_and_realism": { "category": "Photorealistic", "details": "High-fidelity skin rendering with visible tonal variation and natural sheen. Realistic fabric stretch and contouring. No artificial smoothing or stylization." }, "colors_and_tone": { "color_palette": "Warm golden skin tones contrasted with dark neutral clothing and clean white background. Subtle reflections in the black TV surface.", "contrast": "High contrast with strong highlights and deep shadows. Warm color temperature throughout." }, "quality_and_technical_details": { "resolution": "8k ultra high-definition", "details": "Sharp focus on subject with crisp edge definition. Fine detail in hair strands, skin texture, and shadow edges.", "dynamic_range": "High dynamic range preserving highlight detail in sunlit areas while maintaining shadow depth." }, "aspect_ratio_and_output": { "ratio": "3:4" }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve hip-backward posture", "preserve torso twist", "preserve raised arm position", "preserve head turn toward camera" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "maintain strong foreground-to-background separation", "preserve body curvature depth", "retain shadow depth and placement", "prevent flattening of form" ], "recommended_weight": 0.85 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "reduced curves", "flattened hips or chest", "artificial reshaping", "incorrect shadow direction", "soft or diffused shadows inconsistent with sunlight", "overexposed highlights", "loss of skin detail", "lens distortion", "wide-angle exaggeration", "depth flattening", "background clutter", "inconsistent reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions" ] } }
Analyze the input image and identify the main subject: Ragnar, the Viking warrior. Maintain perfect consistency in appearance, proportions, clothing materials, hair, colors, and MAPPA anime style across all frames. Generate a cinematic 9-scene sequence that progresses logically from start to finish based on the following SCENE INPUT: SCENE INPUT: A Viking visits his village after a long time. Constraints: AI chooses all camera angles and framing automatically Cinematic lighting, consistent color grading, realistic depth of field Coherent environmental evolution (snowstorm → village ruins → quiet discovery) Include wind motion in hair, cloak, and snow movement Subtle motion cues for action and atmosphere No repeated shots Frame names explicitly included for extraction Frames Frame 1 — “Village Entrance” Ragnar enters the snowy outskirts of his village, cloak and fur flowing violently in heavy wind, snow falling thickly, distant village structures partially visible, cinematic winter lighting, cold blue tone, subtle movement in snow and hair, MAPPA anime style, reference image used for consistency Frame 2 — “Trudging Through Snow” Medium shot of Ragnar trudging through deep snow, back slightly hunched from cold and emotion, snow-covered trees and fence lines on sides, cinematic depth of field, wind slightly moving cloak and hair, MAPPA anime style Frame 3 — “Face in the Storm” Close-up (head to upper chest) of Ragnar’s face, snow blowing across hair and cloak, restrained emotional expression, breath visible in cold air, cinematic lighting highlighting facial textures, MAPPA anime style Frame 4 — “Glimpse of Ruins” Snow begins to clear subtly, faint glimpse of ruined village structures in distance, Ragnar pauses to survey, wind gently moving hair and cloak, cinematic lighting with soft sunlight breaking through clouds, MAPPA anime style Frame 5 — “Village Ruins Wide” Wide shot of village ruins partially visible under snow, smoke from chimneys, empty streets, broken wooden structures, cinematic winter lighting, wind stirring snow on rooftops, MAPPA anime style Frame 6 — “Wooden Sword Discovery” Medium shot of Ragnar noticing half-buried wooden swords in snow, hand reaching toward them, subtle wind in hair and cloak, snow particles drifting, cinematic depth of field, MAPPA anime style Frame 7 — “Picking Up Sword” Close-up of Ragnar picking up a wooden sword, faint nostalgic smile appearing, snowflakes falling gently around, wind lightly moving cloak and hair, cinematic lighting emphasizing textures, MAPPA anime style Frame 8 — “Approaching House” Medium-wide shot of Ragnar walking toward his old house, wooden walls partially visible through snow and frost, subtle sun breaking through clouds, wind moving cloak and hair, snow drifting, MAPPA anime style Frame 9 — “Silent Confrontation” Wide shot of Ragnar standing in front of his house, snow swirling around him, cloak flowing in wind, heavy silence, cinematic composition, depth of field emphasizing village and foreground snow, MAPPA anime style, perfect character consistency across all frames
Use Long Shot technique: A long shot (LS), also known as a full shot or wide shot, shows the entire human body in frame while including significant portions of the surrounding environment. This shot balances character and setting, showing how subjects interact with their world. Long shots establish spatial relationships and are often used at the beginning of scenes.
{ "subject": { "description": "Young woman with a fair, sunlit complexion and long, voluminous blonde hair styled in loose waves with a soft middle part. Her facial features include full lips with a glossy finish, softly arched eyebrows, and light-colored eyes. Her physique is curvy with a pronounced hourglass silhouette, featuring a narrow waist, wide hips, and a full bust with natural forward projection and soft-tissue behavior. Skin appears smooth with subtle natural texture and warm highlights from direct sunlight.", "attire": "Dark charcoal or black one-piece bodysuit with a high-cut design and side cutouts exposing the waist and lower back. The fabric is smooth and slightly matte with gentle stretch, conforming closely to body contours.", "anatomical_fidelity": "Maintain accurate proportional balance between bust, waist, and hips. Preserve natural soft tissue distribution, especially in hips and thighs, without artificial reshaping or compression. Ensure realistic posture-driven tension across the torso and lower body." }, "pose": { "description": "Standing with her back angled toward the camera, torso twisted to reveal both her back and partial frontal profile. Her hips are pushed slightly backward, emphasizing curvature. One arm is raised with the hand resting on or near her head, while the other arm is relaxed out of frame. Her head is turned toward the camera with a direct, slightly sultry gaze. Spine shows a pronounced natural curve due to the hip shift and twist.", "weight_distribution": "Weight is primarily on the back leg, with the front leg slightly relaxed. This creates a strong hip emphasis and asymmetry through the lower body." }, "environment": { "setting": "Modern indoor living space with minimal decor.", "background": "Clean white walls with a large flat-screen television mounted behind the subject. Subtle reflections on the screen indicate daylight entering from a nearby window. Light wooden flooring visible at the bottom edge.", "foreground": "Strong sunlight casting defined geometric shadows across the subject’s lower body, likely from a window frame or camera rig." }, "camera": { "shot_type": "Medium-full shot", "framing": "Vertical composition capturing from upper head to upper thighs, with emphasis on the hip and torso region.", "perspective": "Slight low to mid-level angle enhancing depth and curvature. Close proximity increases three-dimensional presence.", "lens_characteristics": "Standard focal length (approximately 35mm to 50mm) with mild perspective emphasis, no extreme distortion." }, "lighting": { "type": "Direct natural sunlight", "sources": "Strong sunlight entering from the left side of the frame.", "direction": "Side lighting from camera-left, creating bright highlights on the left side of the body and deeper shadows on the right.", "effects": "High contrast lighting with sharp-edged shadows cast across the hips and thighs. Warm golden tones dominate, with visible light falloff and strong highlight definition on skin." }, "mood_and_expression": { "expression": "Confident and slightly sultry, with relaxed lips and a steady gaze directed toward the camera.", "atmosphere": "Bold, modern, and visually striking due to the interplay of light and shadow." }, "style_and_realism": { "category": "Photorealistic", "details": "High-fidelity skin rendering with visible tonal variation and natural sheen. Realistic fabric stretch and contouring. No artificial smoothing or stylization." }, "colors_and_tone": { "color_palette": "Warm golden skin tones contrasted with dark neutral clothing and clean white background. Subtle reflections in the black TV surface.", "contrast": "High contrast with strong highlights and deep shadows. Warm color temperature throughout." }, "quality_and_technical_details": { "resolution": "8k ultra high-definition", "details": "Sharp focus on subject with crisp edge definition. Fine detail in hair strands, skin texture, and shadow edges.", "dynamic_range": "High dynamic range preserving highlight detail in sunlit areas while maintaining shadow depth." }, "aspect_ratio_and_output": { "ratio": "3:4" }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve hip-backward posture", "preserve torso twist", "preserve raised arm position", "preserve head turn toward camera" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "maintain strong foreground-to-background separation", "preserve body curvature depth", "retain shadow depth and placement", "prevent flattening of form" ], "recommended_weight": 0.85 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "reduced curves", "flattened hips or chest", "artificial reshaping", "incorrect shadow direction", "soft or diffused shadows inconsistent with sunlight", "overexposed highlights", "loss of skin detail", "lens distortion", "wide-angle exaggeration", "depth flattening", "background clutter", "inconsistent reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions" ] } }
of the input image and identify all main subjects and the environment. Generate high-quality 3x3 grid, a cinematic contact sheet with 9 frames of the same scene. Strictly preserve objects, proportions, setting, lighting direction, style, and overall visual mood of the original image. Vary only the camera parameters: distance (close- up, medium shot, wide shot), angle (frontal, slight low angle, side), depth of field, and focus point. Do not add new elements or alter the design of the subjects;
Analyze the input image and identify the main subject: Ragnar, the Viking warrior. Maintain perfect consistency in appearance, proportions, clothing materials, hair, colors, and MAPPA anime style across all frames. Generate a cinematic 9-scene sequence that progresses logically from start to finish based on the following SCENE INPUT: SCENE INPUT: A Viking visits his village after a long time. Constraints: AI chooses all camera angles and framing automatically Cinematic lighting, consistent color grading, realistic depth of field Coherent environmental evolution (snowstorm → village ruins → quiet discovery) Include wind motion in hair, cloak, and snow movement Subtle motion cues for action and atmosphere No repeated shots Frame names explicitly included for extraction Frames Frame 1 — “Village Entrance” Ragnar enters the snowy outskirts of his village, cloak and fur flowing violently in heavy wind, snow falling thickly, distant village structures partially visible, cinematic winter lighting, cold blue tone, subtle movement in snow and hair, MAPPA anime style, reference image used for consistency Frame 2 — “Trudging Through Snow” Medium shot of Ragnar trudging through deep snow, back slightly hunched from cold and emotion, snow-covered trees and fence lines on sides, cinematic depth of field, wind slightly moving cloak and hair, MAPPA anime style Frame 3 — “Face in the Storm” Close-up (head to upper chest) of Ragnar’s face, snow blowing across hair and cloak, restrained emotional expression, breath visible in cold air, cinematic lighting highlighting facial textures, MAPPA anime style Frame 4 — “Glimpse of Ruins” Snow begins to clear subtly, faint glimpse of ruined village structures in distance, Ragnar pauses to survey, wind gently moving hair and cloak, cinematic lighting with soft sunlight breaking through clouds, MAPPA anime style Frame 5 — “Village Ruins Wide” Wide shot of village ruins partially visible under snow, smoke from chimneys, empty streets, broken wooden structures, cinematic winter lighting, wind stirring snow on rooftops, MAPPA anime style Frame 6 — “Wooden Sword Discovery” Medium shot of Ragnar noticing half-buried wooden swords in snow, hand reaching toward them, subtle wind in hair and cloak, snow particles drifting, cinematic depth of field, MAPPA anime style Frame 7 — “Picking Up Sword” Close-up of Ragnar picking up a wooden sword, faint nostalgic smile appearing, snowflakes falling gently around, wind lightly moving cloak and hair, cinematic lighting emphasizing textures, MAPPA anime style Frame 8 — “Approaching House” Medium-wide shot of Ragnar walking toward his old house, wooden walls partially visible through snow and frost, subtle sun breaking through clouds, wind moving cloak and hair, snow drifting, MAPPA anime style Frame 9 — “Silent Confrontation” Wide shot of Ragnar standing in front of his house, snow swirling around him, cloak flowing in wind, heavy silence, cinematic composition, depth of field emphasizing village and foreground snow, MAPPA anime style, perfect character consistency across all frames
Use Long Shot technique: A long shot (LS), also known as a full shot or wide shot, shows the entire human body in frame while including significant portions of the surrounding environment. This shot balances character and setting, showing how subjects interact with their world. Long shots establish spatial relationships and are often used at the beginning of scenes.
of the input image and identify all main subjects and the environment. Generate high-quality 3x3 grid, a cinematic contact sheet with 9 frames of the same scene. Strictly preserve objects, proportions, setting, lighting direction, style, and overall visual mood of the original image. Vary only the camera parameters: distance (close- up, medium shot, wide shot), angle (frontal, slight low angle, side), depth of field, and focus point. Do not add new elements or alter the design of the subjects;
{ "subject": { "description": "Young woman with a fair, sunlit complexion and long, voluminous blonde hair styled in loose waves with a soft middle part. Her facial features include full lips with a glossy finish, softly arched eyebrows, and light-colored eyes. Her physique is curvy with a pronounced hourglass silhouette, featuring a narrow waist, wide hips, and a full bust with natural forward projection and soft-tissue behavior. Skin appears smooth with subtle natural texture and warm highlights from direct sunlight.", "attire": "Dark charcoal or black one-piece bodysuit with a high-cut design and side cutouts exposing the waist and lower back. The fabric is smooth and slightly matte with gentle stretch, conforming closely to body contours.", "anatomical_fidelity": "Maintain accurate proportional balance between bust, waist, and hips. Preserve natural soft tissue distribution, especially in hips and thighs, without artificial reshaping or compression. Ensure realistic posture-driven tension across the torso and lower body." }, "pose": { "description": "Standing with her back angled toward the camera, torso twisted to reveal both her back and partial frontal profile. Her hips are pushed slightly backward, emphasizing curvature. One arm is raised with the hand resting on or near her head, while the other arm is relaxed out of frame. Her head is turned toward the camera with a direct, slightly sultry gaze. Spine shows a pronounced natural curve due to the hip shift and twist.", "weight_distribution": "Weight is primarily on the back leg, with the front leg slightly relaxed. This creates a strong hip emphasis and asymmetry through the lower body." }, "environment": { "setting": "Modern indoor living space with minimal decor.", "background": "Clean white walls with a large flat-screen television mounted behind the subject. Subtle reflections on the screen indicate daylight entering from a nearby window. Light wooden flooring visible at the bottom edge.", "foreground": "Strong sunlight casting defined geometric shadows across the subject’s lower body, likely from a window frame or camera rig." }, "camera": { "shot_type": "Medium-full shot", "framing": "Vertical composition capturing from upper head to upper thighs, with emphasis on the hip and torso region.", "perspective": "Slight low to mid-level angle enhancing depth and curvature. Close proximity increases three-dimensional presence.", "lens_characteristics": "Standard focal length (approximately 35mm to 50mm) with mild perspective emphasis, no extreme distortion." }, "lighting": { "type": "Direct natural sunlight", "sources": "Strong sunlight entering from the left side of the frame.", "direction": "Side lighting from camera-left, creating bright highlights on the left side of the body and deeper shadows on the right.", "effects": "High contrast lighting with sharp-edged shadows cast across the hips and thighs. Warm golden tones dominate, with visible light falloff and strong highlight definition on skin." }, "mood_and_expression": { "expression": "Confident and slightly sultry, with relaxed lips and a steady gaze directed toward the camera.", "atmosphere": "Bold, modern, and visually striking due to the interplay of light and shadow." }, "style_and_realism": { "category": "Photorealistic", "details": "High-fidelity skin rendering with visible tonal variation and natural sheen. Realistic fabric stretch and contouring. No artificial smoothing or stylization." }, "colors_and_tone": { "color_palette": "Warm golden skin tones contrasted with dark neutral clothing and clean white background. Subtle reflections in the black TV surface.", "contrast": "High contrast with strong highlights and deep shadows. Warm color temperature throughout." }, "quality_and_technical_details": { "resolution": "8k ultra high-definition", "details": "Sharp focus on subject with crisp edge definition. Fine detail in hair strands, skin texture, and shadow edges.", "dynamic_range": "High dynamic range preserving highlight detail in sunlit areas while maintaining shadow depth." }, "aspect_ratio_and_output": { "ratio": "3:4" }, "controlnet": { "pose_control": { "model_type": "DWPose", "purpose": "Exact skeletal and pose lock", "constraints": [ "preserve hip-backward posture", "preserve torso twist", "preserve raised arm position", "preserve head turn toward camera" ], "recommended_weight": 1.0 }, "depth_control": { "model_type": "ZoeDepth", "purpose": "Depth, volume, and camera-to-body spatial lock", "constraints": [ "maintain strong foreground-to-background separation", "preserve body curvature depth", "retain shadow depth and placement", "prevent flattening of form" ], "recommended_weight": 0.85 } }, "negative_prompt": { "forbidden_elements": [ "anatomy normalization", "body proportion averaging", "reduced curves", "flattened hips or chest", "artificial reshaping", "incorrect shadow direction", "soft or diffused shadows inconsistent with sunlight", "overexposed highlights", "loss of skin detail", "lens distortion", "wide-angle exaggeration", "depth flattening", "background clutter", "inconsistent reflections", "beautification filters", "skin smoothing", "plastic skin", "airbrushed texture", "stylized realism", "editorial fashion proportions" ] } }