Videos Images
Sign in
GPT Image 2 Identity-Preserving Portrait Prompt

GPT Image 2 Identity-Preserving Portrait Prompt

views20,200
likes225
comments4
shares35
bookmarks190
quotes0
Translated
Please use only the photos I uploaded as a reference for the person's identity to preserve my real appearance. Do not retain the background, clothes, props, sitting posture, or shooting environment from the original photo. Please generate a brand new {argument name="写真类型" default="鬼马少女棚拍写真"}.

Please strictly preserve my real identity features, including face shape, facial proportions, eyes, nose, lips, skin color, age appearance, hairline, hairstyle foundation, and overall temperament. Do not turn into a stranger, do not Europeanize, do not over-beautify, do not create an AI fake face.

For the hairstyle, please extend naturally based on the uploaded photo:
- Hair length should remain at the same level
- Whether there are bangs should follow the original image
- If the original image is black hair, please process it into dark brown-black, black tea color, or natural dark coffee color, do not make it pure black or dead black
- Only optimize for photo shoots, do not change the hairstyle drastically

Makeup should be unified as {argument name="妆容风格" default="韩系鬼马少女妆"}: 
Clear and dewy cream skin, natural flat eyebrows, light pink-brown or peach pink eye makeup, prominent aegyo sal, long and thin eyelashes, fine eyeliner, large areas of pink or peach pink blush extending under the eyes with a bit of redness on the nose tip, lips in watery strawberry pink or peach pink. Overall sweet, spirited, playful, no heavy makeup, no European makeup.

Overall style is {argument name="视觉风格" default="韩系少女杂志感、鬼马感、甜酷混合、精致棚拍写真"}. The background is a light gray-white or milky white seamless photography studio background, with soft and bright lighting, clean and clear visuals, with a slight film grain and editorial texture.

Machine-translated — the original is what produced this result.

✨ Generate Original post Open in Hitboard

How to use this prompt

Copy the prompt and paste it into GPT Image 2. Keep the composition, lighting and style terms as written — they are what produced this result. Swap the subject or scene details to make it yours, keep the aspect ratio, and attach the reference images the prompt mentions if any. Regenerate two or three times; the strongest version is usually not the first.