Image prompt
A high-fidelity prompt for studio-quality portraits inside a luxury car, emphasizing identity preservation from a reference photo and a modern Korean aesthetic.
Copy directly into the target model and adjust for your input assets.
Use my uploaded face photo as the only facial identity reference and preserve the exact same person with 99–100% facial similarity. Do not change facial structure, skin tone, ethnicity, facial proportions, eyes, nose, lips, jawline, cheekbones, or natural skin texture. Create a {argument name="subject" default="young woman (23)"} with subtle glossy Douyin-style makeup, luminous realistic skin, soft peach blush, natural lashes, and coral-red lips. Match the reference image’s {argument name="hair style" default="long straight black center-parted hair"}, {argument name="clothing" default="cream-white oversized sweatshirt"}, pearl necklace, manicure, pose, camera angle, composition, luxury car interior, and daylight lighting exactly. The subject is seated inside a luxury vehicle, extending one hand toward the camera with strong foreground perspective, direct eye contact, and a calm confident expression. Professional DSLR photography, 24–35mm lens, RAW realism, ultra-sharp details, realistic pores, hair strands, fabric textures, shallow depth of field, clean HDR color grading, modern Korean luxury aesthetic, 8K commercial fashion quality. Remove all text, logos, watermarks, and AI artifacts. Negative prompt: anime, manga, cartoon, CGI, illustration, beauty filters, plastic skin, identity blending, face morphing, new facial features, outdoor scenery, flowers, sunset, lens flare, extra fingers, bad anatomy, blur, watermark, logo, text. --ar 9:16 --style raw --quality high --photorealistic --identity preservation maximum.
Original source details are kept for attribution and review.
GitHub source：YouMind-OpenLab/gpt-image-2-prompts-search
This page is adapted from YouMind OpenLab GitHub prompt libraries. License: MIT。