GPT Image Prompt
Photorealistic vertical indoor fashion portrait of the same young woman from the Knowledge reference set, preserving her exact face identity, natural long-leg body proportions, hair identity, facial geometry, eye shape, nose, lips, jawline, and overall realistic anatomy. She has long brown hair with natural strands and subtle flyaways, calm direct eye contact, and a soft intimate expression.
She wears a lavender floral dress with delicate lace trim and a sheer embroidered outer layer, styled with a black choker necklace, layered pendant necklaces, and small hoop earrings. The fabric should look realistic, with natural thickness, embroidery detail, seams, folds, soft drape, and believable material response to warm indoor light.
Pose her close to the camera, seated or standing naturally while facing forward, relaxed shoulders, graceful posture, hands either softly resting out of focus or gently placed in a natural position. Keep the body proportions realistic and elegant, with correct perspective, natural neck and shoulder structure, realistic hands and fingers, and no distorted anatomy.
Camera and lighting: vertical realistic portrait photo, intimate close portrait or upper-body framing, eye-level camera, natural 50mm portrait lens feel, shallow depth of field focused on her face and jewelry. Warm natural window light softly illuminates her face and dress, with gentle shadows, clean skin texture, visible natural pores where close enough, realistic eyes, lashes, lips, and hair detail. The color tone is romantic, soft, vintage-inspired, and warm without fake HDR or heavy overprocessing.
Environment: vintage-style indoor room with a teal floral wall, an antique mirror, and softly lit romantic room styling in the background. The room should feel real, intimate, and fashion-editorial, with believable wall texture, mirror reflection behavior, natural depth, and warm window-light atmosphere.
Foreground and midground wall, floral wallpaper, mirror edges, fabric, jewelry, and visible room textures remain clear, organic, and photographically readable; only the far background may soften slightly with natural depth of field. Avoid AI-pattern artifacts and blurry mush.
Negative prompt: different face, changed identity, plastic skin, over-smoothed beauty filter, bad anatomy, distorted hands, extra fingers, missing fingers, fused fingers, warped limbs, oversized head, shortened legs, see-through clothing, underwear, lingerie, AI texture hallucination, repeated wallpaper patterns, smeared wall texture, fake mirror reflection, fake HDR, excessive sharpening, CGI, text artifacts, 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”.