GPT Image Prompt
Photorealistic casual smartphone-style studio portrait of the exact same adult woman from the LoRA identity reference images. Preserve her exact facial identity and body identity: same face geometry, eye spacing, eye shape, nose, lips, jaw, cheek structure, hair identity, skin tone, shoulder width, torso-to-leg balance, natural waist thickness, hip width, thigh volume, leg length ratio, and overall body mass distribution. Do not make her slimmer, taller, longer-legged, more hourglass, more model-like, or more influencer-like than the reference.
Scene: plain white seamless cyclorama studio with a simple white wall and white floor, minimal clean background, realistic floor texture, subtle scuffs, soft natural studio lighting, mild contact shadows, physically grounded environment.
Subject outfit: crisp white button-up dress shirt with collar, slightly relaxed fit, sleeves casually rolled or pushed up, loosened black necktie hanging naturally down the front, black high-waisted fitted mini skirt, black pointed-toe heels. The styling is monochrome, clean, business/school-uniform inspired, modest and non-explicit. No cleavage emphasis, no erotic styling.
Pose: single-knee kneeling pose on the studio floor. One knee rests on the floor with realistic pressure and contact shadow, the other leg bent forward with foot planted naturally. Torso upright, shoulders relaxed, body facing mostly toward camera. One hand rests naturally near the raised thigh/knee, the other hand relaxed near the side or lower thigh. Hands have correct finger count, natural finger spacing, realistic wrist angles, and believable fabric contact.
Expression: calm confident natural expression, direct soft gaze toward the camera, relaxed mouth, alive eyes, subtle asymmetry, composed but not seductive, not theatrical, not blank or mannequin-like.
Camera: realistic handheld iPhone-style smartphone photo, vertical 3:4 frame, casual low crouched camera position at about knee-to-waist height, mild upward angle but not extreme, no body distortion, no leg elongation. Imperfect casual framing, slight handheld imbalance, realistic smartphone wide-angle perspective, small-sensor depth behavior, mild computational sharpness variation, natural auto exposure, subtle compression and texture inconsistency.
Image realism: natural skin texture, visible but not exaggerated pores, realistic fabric wrinkles, slight uneven sharpness, soft practical shadows, believable floor contact, ordinary smartphone realism. Avoid cinematic fashion editorial polish, dramatic lighting, DSLR bokeh, influencer aesthetics, seductive framing, cleavage emphasis, exaggerated curves, waist slimming, hip narrowing, thigh reduction, leg elongation, plastic skin, airbrushing, over-sharpening, fake HDR, CGI texture, watermark, text, logo.
Negative prompt:
extreme low angle, boyfriend POV, seductive, lustful, cleavage emphasis, erotic pose, exaggerated curves, hourglass body, long legs, slim waist, narrow hips, reduced thighs, influencer beauty, fashion editorial, cinematic lighting, DSLR bokeh, plastic skin, airbrushed skin, over-sharpened, fake HDR, broken hands, fused fingers, duplicated fingers, floating knee, disconnected shadows, mannequin expression, blank stare
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”.