GPT Image Prompt
Photorealistic casual iPhone-style vertical photo of the exact same real woman from the active LoRA identity reference, with LoRA face and full-body identity continuity protected first: preserve her recognizable facial geometry, soft oval face structure, exact eye spacing and eye shape, natural lips, jaw and cheek structure, long dark loose hair identity, light warm skin tone, shoulder-to-head relationship, shoulder width, torso length, torso-to-leg balance, waist thickness, hip width, thigh volume, knee-to-ankle scale, natural body mass distribution, and her grounded seated physical presence. Do not beautify, slim, elongate, narrow, curve-enhance, reshape, or substitute her body with a more model-like version. The final subject must remain unmistakably the same LoRA woman in both face and body, not a similar attractive substitute.
She is seated on a bed in a bright hotel-bedroom interior, leaning back naturally against a textured wall or headboard, torso angled slightly toward the camera, left arm dropped loosely along the wall side, right hand planted into the wrinkled white bedding for support with believable palm pressure and wrist tension, knees forward near the lower crop. Her posture feels physically relaxed and weight-bearing, with natural seated compression, realistic balance, and imperfect human asymmetry. Preserve the original quiet human moment: relaxed eyelids, a soft camera-aware glance, lips gently parted, calm tired softness in the face, alive and newly captured rather than blank, stiff, mannequin-like, seductive, or commercially posed.
She wears the same white sleeveless fitted knit dress with thin straps, low neckline, slight ribbed texture, natural fabric stretch, small wrinkles, subtle uneven hem, and realistic fabric tension over the same LoRA body proportions without reshaping the waist, hips, thighs, torso, or seated silhouette. Add delicate small earrings and a thin necklace. Hair falls loosely with stray strands and casual imperfection, not salon-polished.
The room is an ordinary bright hotel-bedroom setting with believable spatial scale: wrinkled white bedding, curtain, bedside lamp, bed, window, wall or headboard, and practical background clutter or slight asymmetry visible. Bright daylight comes from the right-side window, causing clipped highlights on the bedding and white dress, soft compressed shadows on the face, mild exposure imbalance, and uneven smartphone HDR reconstruction. Lighting must feel like real daylight entering a hotel room, not studio lighting or cinematic setup.
All expression, gesture, outfit, seated pose, camera behavior, lighting, hotel-room realism, smartphone imperfections, fabric behavior, and scene details remain subordinate to the active LoRA identity reference. The final image must still be unmistakably the exact same LoRA subject in face, body geometry, proportions, hair identity, skin tone, and recognizable physical presence, not a beautified replacement, not a generic attractive woman, not a face pasted onto a different body, and not an influencer-style reinterpretation.
Capture as a close handheld iPhone-style vertical photo with casual imperfect framing, mild wide-angle smartphone perspective, slight crop imbalance, knees near the lower edge, natural room scale, and ordinary private indoor-photo energy. Allow subtle smartphone artifacts: uneven sharpness, slight local softness, mild edge reconstruction inconsistency, natural skin texture with light denoise softness, realistic compression, imperfect HDR, and small-sensor depth behavior. Avoid cinematic polish, DSLR bokeh, luxury editorial composition, influencer glamour, beauty-filter skin, over-smoothed face, hyper-clean rendering, artificial symmetry, perfect framing, fashion-model posture, seductive gaze, fake commercial smile, blank stare, dead eyes, mannequin stiffness, plastic hands, fused fingers, floating limbs, disconnected shadows, unrealistic bedding contact, impossible body balance, waist slimming, hip narrowing, thigh reduction, leg elongation, torso narrowing, hourglass enhancement, or any smartphone angle that changes the LoRA reference body identity.
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.