GPT Image Prompt
Photorealistic 9:16 vertical full-body studio fashion portrait of the same young adult female visual character from the reference set, preserving her recognizable facial geometry, natural long-leg body proportions, realistic head-to-body balance, and consistent identity without beautifying her into a different person. She stands front-facing with slight casual asymmetry in a sporty, confident, youthful editorial streetwear pose: head facing forward, direct eye contact, calm neutral expression with a soft confident presence, shoulders relaxed and slightly uneven because one arm is raised, one hand resting near or lightly touching a white knit beanie, the other arm relaxed downward with the long sleeve covering part of the hand, weight mostly on one leg with a relaxed hip shift, one leg straight as the main support and the other slightly bent and crossed forward casually.
She has long loose wavy hair with a brown base and vivid multicolor streaks in pink, teal, orange, and purple, partially covered by the white knit beanie, with realistic individual strands, soft volume, and believable dyed color transitions. Outfit: an oversized white graphic T-shirt layered over a black long-sleeve top, black sporty shorts with a white graphic print and a red ribbon strap accent, black mid-calf socks with subtle white lettering, bright red chunky sneakers, and a thin black choker necklace. Preserve the oversized sporty streetwear silhouette, black-white-red color blocking, layered styling, knit beanie texture, clear but not garbled graphic print treatment, realistic sock ribbing, and detailed sneaker structure, laces, and material texture.
Environment: a clean controlled studio fashion setup with a smooth seamless backdrop, yellow-green gradient on the left and cyan-blue gradient on the right, with a clean floor transition and minimal but believable contact shadow near the shoes. Composition: centered subject with balanced negative space, full-body portrait framing, full-body portrait distance, chest-level to eye-level camera height, front-facing camera angle, 35mm lifestyle lens feel, deep focus, realistic scale relationship between subject and backdrop, straight vertical framing, and no exaggerated lens distortion.
Lighting: clean softbox studio lighting with soft front-top illumination and gentle fill, soft and even light quality, subtle contact shadow on the floor, controlled highlights on skin, hair, white shirt, and beanie without clipping, bright even exposure, medium contrast, neutral daylight white balance, high saturation in the gradient background, red shoes, graphic accents, and hair streaks while keeping skin tones natural.
Quality intent: premium camera-plausible photorealism, crisp natural subject detail, natural skin texture with visible pores and subtle micro-detail, realistic eyes, lashes, lips, and facial structure, natural hair strands and flyaways, realistic cotton shirt texture, knit beanie texture, sporty fabric response, folds, wrinkles, seams, thickness, and drape, correct anatomy, correct hands and fingers where visible, realistic perspective, believable contact shadow, and a realistic seamless studio background with no fake cutout look.
Negative prompt: low quality, blurry face, over-smoothed skin, plastic skin, doll-like face, bad anatomy, distorted hands, extra fingers, missing fingers, fused fingers, warped limbs, broken joints, short legs, oversized head, long torso with short legs, deformed face, asymmetrical eyes, fake background, inconsistent lighting, floating subject, wrong perspective, duplicated objects, CGI, anime, cartoon, fake HDR, excessive sharpening, text artifacts, logo errors, watermark.
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”.