artificial lighting Nano Banana prompts

21 days ago

A hyper-credible sun-facing selfie (not a mirror shot; no phone visible) captured on an iPhone 16 Pro Max. Subject: the uploaded woman Hair: Makeup: subtle black eyeliner, matte lipstick; natural pores (no beauty filter). Expression (shocked): brows lifted and knit; eyes wide with bright catchlights; pupils slightly constricted by sun; mouth parted in a small inhale (not exaggerated); faint cheek/neck tension; micro-sheen on T-zone from heat. Wardrobe (tank top + accessories): matte ribbed cotton tank top in desaturated slate blue (no logos), scooped neckline, thick straps, relaxed fit; soft fabric micro-creases from movement, no plasticky shine. Accessories: tiny silver huggie hoops; two thin layered silver necklaces (one short box chain with a 2–3 mm disc pendant, one slightly longer cable chain); fabric-strap field watch (olive) on left wrist; woven paracord bracelet (neutral) on right wrist; a slim tan canvas cross-body strap from a small pouch just grazing the frame edge (bag itself mostly out of frame). Jewelry is low-gloss so it doesn’t flare; keep silhouettes clean and non-distracting. Moment: behind her, a realistic, predatory dinosaur (T. rex-like) leaping from foliage—low, sneaky posture; mouth slightly open with saliva filaments; cat-like focused eye; fine scales and muscular anatomy; dust/leaf debris kicked up. Lighting & look: broad noon daylight in a lush jungle (large leaves, sun shafts). Sun is the key in front of her (10–11 o’clock) for crisp, short shadows and hair rim-sparkles; use natural ground/leaf bounce as fill (key:fill ≈ 3:1) so shadows stay readable. Feather highlights—no blown hotspots on cheeks/forehead. Dynamic range preserved (retain sky/leaf detail); no obvious filters. If supported, apply background-only micro-motion blur and handheld micro-shake while keeping her face tack-sharp. Framing & optics: vertical portrait selfie at arm-length, slight wide-angle feel; background compressed enough to keep the dinosaur readable. Shallow DoF from close focus on her face—eyes ultra-sharp; controlled speculars along hair layers; distinct catchlights in eyes. Environment: humid air; faint pollen/dust motes; torn leaves mid-air; scuffed ground. Color: sunlit greens; warm, lifelike skin; dinosaur hues olive/umber/ash—not plastic. Hard rules: do not show a phone; selfie (not mirror); no stylized filters; no heavy shadows; adult subject. Avoid: plastic toy textures, CGI gloss, grim darkness, lens flares across face, exaggerated depth warping, artificial makeup blur.

1 month ago

Build a two-story cottage with large windows in a modern style. Surrounded by forest and lots of artificial light. There is a garage and a swimming pool.

13 hours ago

Scientific infographic illustrating an AI-driven closed-loop framework for virtual molecular library construction, showing the adaptive cycle of “Representation – Generation – Prediction – Feedback”. Central theme: artificial intelligence empowering drug discovery and molecular design. The diagram is a circular workflow structure centered on the AI virtual molecular library system. Left module: Representation Learning, visualized with neural network icons, molecular graphs, protein structures, and amino acid sequence symbols, representing molecular and protein feature embeddings. Upper-right module: Molecular Generation, showing diffusion or VAE-like model generating diverse small molecules, arrows indicating exploration of chemical space, novelty, and synthesizability constraints. Lower-right module: Property Prediction, containing ADMET, activity, and selectivity metrics represented by radar charts or data panels, feeding results back to the representation module to close the loop. Bottom section: Evolution from virtual to drug-like molecular libraries, shown as a smooth gradient arrow with multi-objective optimization icons balancing drug-likeness and diversity. Right-side branch: Pretrained models for new target ligand design, divided into three submodules—small molecule pretraining, protein pretraining, and cross-modal pretraining (protein–ligand interaction)—depicting embedding fusion or contrastive learning in shared latent space. No human figures, only abstract scientific symbols and molecular visuals. Style: flat vector scientific infographic, modern and minimalistic, clear logical flow, smooth connections between modules. Color scheme: blue for AI and representation, orange-yellow for generation, green for prediction; background light gray or white. Typography: clean sans-serif labels, concise annotations. High resolution (≥600 dpi), suitable for journal publication, ultra-clear, balanced layout, professional academic tone.