GPT Image Prompt
A realistic casual vertical iPhone-style beach snapshot of the exact same young woman from the active LoRA identity reference, preserving her structural face identity and full-body identity before all other instructions: same recognizable facial geometry, eye spacing, eye shape, nose, lips, jaw, cheeks, skull proportions, warm skin tone, long dark wavy hair identity, narrow relaxed shoulder width, natural body proportions, torso-to-leg balance, waist thickness, hip width, thigh volume, leg length ratio, body mass distribution, and grounded adult height impression. Do not make her taller, slimmer, curvier, longer-legged, narrower-waisted, narrower-hipped, reduced-thigh, more model-like, or more influencer-like than the LoRA reference.
She is standing on uneven beach sand in a casual vacation pose, torso mostly facing forward with a slight side lean and natural hip shift, weight unevenly settled into the sand. One arm is raised diagonally above her head with a small casual finger gesture, with natural wrist articulation and correct finger count. The other arm hangs naturally near her side while gripping a large red-and-navy tote bag close to her thigh; the bag hangs with believable weight, fabric sag, hand pressure, and natural grip tension. Her feet stay physically grounded in the textured sand with believable contact shadows, slight shoe pressure, and no floating or detached stance.
Keep the exact outfit behavior from the source prompt: yellow cropped fitted T-shirt with dark front lettering, red short shorts with white side text and waist tie detail, red sneakers, white socks, light yellow baseball cap, bracelets, rings, and dark wristband. Clothing should sit on her LoRA body naturally without reshaping her silhouette, with realistic fabric tension, small folds, casual beach wear behavior, and no fashion-editorial styling.
Her face is caught in a fresh relaxed beach moment: softened camera-aware glance from under the cap, slightly narrowed eyes from bright coastal glare, and a faint uneven half-smile that feels calm, lightly playful, and alive. Preserve the human moment from the source prompt while keeping the LoRA facial structure intact. Do not copy blank LoRA-reference stiffness, dead eyes, frozen mouth, mannequin neutrality, seductive influencer gaze, commercial smile, or theatrical emotion.
The setting is an ordinary cloudy beach shoreline, not a staged luxury location: large rocks on the left, ocean waves behind her, textured uneven sand underfoot, and a small table edge partly visible in the foreground. The environment should feel physically real, casually cluttered, imperfect, and naturally scaled, with believable shoreline depth, real sand texture, wave softness, rock scale, imperfect background overlap, and natural beach haze.
All expression, gesture, outfit, pose, camera, lighting, and realism behavior remain subordinate to the active LoRA identity reference. The final subject must still be unmistakably the exact same LoRA woman in both face and body, not a similar-looking substitute, not a beautified replacement, not the same face on a different body, and not a generic attractive version of the beach prompt.
Photograph as if taken by another person using a handheld iPhone in casual vertical framing. Use mild wide-angle smartphone perspective without altering body identity, slight crop imbalance, imperfect centering, a small handheld tilt, ordinary vacation-snapshot distance, and socially believable capture timing. Preserve casual smartphone optics: small-sensor depth behavior, no DSLR compression, no cinematic bokeh, no perfect subject isolation, no studio alignment, no luxury editorial composition.
Lighting should feel like cloudy coastal daylight with natural beach glare, cap shadow across the face, uneven smartphone auto-exposure, imperfect HDR in the cloudy sky and ocean, mild highlight clipping where believable, slightly compressed shadows, and realistic skin response. Keep natural hair softness and wind-affected unevenness, with long dark wavy hair falling loosely over both shoulders and minor strand irregularity.
Add controlled real-phone imperfection: uneven sharpness across hair, face, tote fabric, sand, and rocks; subtle compression softness; slight smartphone ISP reconstruction artifacts; mild edge softness; imperfect texture recovery; natural skin texture without beauty-filter smoothing; ordinary environmental contamination; no globally perfect detail. The image should feel photographed, not rendered.
Negative restrictions: no cinematic grading, no DSLR blur, no beauty-filter polish, no influencer body reshaping, no waist slimming, no hip narrowing, no thigh reduction, no leg elongation, no model-like posture, no fashion pose conversion, no over-clean AI rendering, no plastic skin, no hyper-symmetry, no fake HDR glow, no luxury beach editorial look, no mannequin expression, no fused fingers, no duplicated fingers, no broken wrists, no floating bag, no disconnected feet, no detached shadows, no impossible beach geometry, and no polished social-media perfection.
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”.