GPT Image Prompt
Photorealistic casual iPhone-style beach photo of the exact same young woman from the active LoRA identity reference, preserving her full structural identity before anything else: recognizable oval facial structure, original eye spacing and eye shape, nose–lip–jaw relationship, cheek and chin geometry, fair daylight skin tone, long straight black hair falling heavily over one shoulder, same shoulder-to-head relationship, same shoulder width, same torso length, same torso-to-leg balance, same waist thickness, same hip width, same thigh volume, same leg length ratio, and same natural body mass distribution. Do not beautify, slim, elongate, reshape, or replace her body with a more model-like silhouette.
She is standing upright near dark seaside rocks with turquoise ocean and clear blue sky behind her, casually captured in a real tourist snapshot moment. Her head is turned slightly to her left, her eyes glance slightly downward off-camera with relaxed daylight-softened lids, and her lips are softly parted. Her expression feels calm, mildly distracted, and alive, not stiff, blank, posed, seductive, or mannequin-like. Both elbows are bent forward, with her hands lightly hovering near the top area of her outfit as if caught mid-adjustment; fingers are relaxed, naturally imperfect, slightly uneven, and physically believable, with correct finger count, natural spacing, realistic wrist flow, and no rigid fashion-pose hand styling.
She wears the same pale aqua strapless tie-front cropped top with dangling center strings, light blue high-waisted frayed denim shorts with distressed side openings, a small black shoulder bag with a thin chain strap resting on her left side, and a dark bracelet or watch on her right wrist. Clothing must sit naturally on the exact LoRA body geometry, with realistic fabric tension, natural waist and hip continuity, visible frayed denim threads, and no outfit-driven body reshaping.
All expression, gesture, outfit, pose, camera angle, lighting, framing, and realism behavior remain subordinate to the active LoRA identity reference. The final subject must be unmistakably the exact same LoRA woman in both face and body, not a similar-looking substitute, not a beautified replacement, not a generic attractive beach model, and not the same face placed onto a different body type.
Bright midday coastal sunlight, real smartphone exposure imbalance, slightly strong skin highlights, saturated turquoise water, clear blue sky, mild HDR processing, uneven sharpness, subtle compression softness, natural hair-edge imperfection, rough dark rock texture, realistic contact shadows, believable environmental scale, grounded stance, casual handheld iPhone framing, slight framing asymmetry, mild wide-angle smartphone perspective without slimming the waist, elongating legs, narrowing hips, or reducing thigh volume. Ordinary social smartphone photo realism, imperfect capture timing, small-sensor depth behavior, slight edge softness, natural environmental clutter and coastal texture variation.
Avoid cinematic lighting, editorial fashion composition, influencer beach posing, luxury travel-photo polish, over-smoothed skin, plastic skin, CGI texture, perfect symmetry, exaggerated bokeh, fake HDR perfection, over-sharpening, mannequin expression, blank stare, dead eyes, seductive gaze, commercial smile, body slimming, waist compression, hip narrowing, thigh reduction, leg elongation, generic model proportions, disconnected hands, fused fingers, melted fingers, floating limbs, fake contact shadows, impossible perspective, and any aesthetic optimization that changes the LoRA face or 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”.