GPT Image Prompt
Edit the provided image using my uploaded face photo as the only facial identity reference. Absolute face preservation mode, strict face lock. Preserve 95–100% facial similarity: exact eyes, eyelids, brows, nose, lips, jawline, cheekbones, forehead, skin tone, ethnicity, age appearance, facial proportions, recognizable identity, natural skin texture, pores, and subtle imperfections. Do not create a new person, beautify, or blend identities. Face = my photo only. Hairstyle, outfit, pose, lighting, color grading, environment, and composition = reference image. Priority: face > pose > lighting > environment > outfit.
Create an ultra-photorealistic vertical 9:16 DSLR portrait of a 23-year-old woman in a dark minimalist studio. She has a shy mysterious expression, subtle intimate eye contact, realistic feminine proportions, and natural low-light skin detail.
Use the exact reference pose: peeking from behind a vertical wall/panel, one hand gripping the upper edge, the other holding the side edge, partial body reveal, face emerging from the side, same head angle and portrait framing.
Hair: long straight slightly messy dark brown/black hair from the reference image only, with wispy face-framing strands, natural volume, individual hairs, soft shine, and backlit rim glow. Ignore hairstyle from the face photo.
Makeup: subtle glossy Douyin clean-beauty makeup, luminous skin, soft peach blush, warm nude-brown eyeshadow, thin eyeliner, natural lashes, glossy nude lips. No heavy glam, no beauty filter.
Outfit: oversized matte-black hoodie, relaxed fit, long sleeves, realistic folds, premium textile texture. No accessories.
Environment: pure black background, dark minimalist studio, clean negative space, no outdoor scenery, flowers, garden, room décor, or decorative elements.
Lighting: low-key DSLR studio lighting, strong rear rim light, soft frontal facial illumination, glowing hair edges, dramatic side contrast, glossy facial highlights, deep shadow falloff, cinematic separation from black background.
Camera/style: 85mm DSLR portrait lens, shallow depth of field, RAW realism, ultra-sharp face detail, realistic anatomy, luxury fashion editorial quality, commercial portrait realism, dark cinematic color grading, warm amber highlights, muted blacks, subtle rim glow, soft bloom, 8K detail.
Remove watermark, logo, and text.
Negative prompt: anime, manga, cartoon, illustration, CGI, plastic skin, beauty filter, identity blending, different person, wrong face, wrong pose, wrong lighting, bright background, garden, flowers, outdoor sunlight, room interior, kimono, hanfu, bright clothing, jewelry, bad anatomy, oversmoothed skin, watermark, logo, text. --ar 9:16 --style raw --quality high
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”.