Original document
GPT Image 2 · en
Ultra-realistic Japanese high school yearbook portrait of a {argument name="subject" default="beautiful teenage girl"}, centered in a formal graduation photo layout. She has {argument name="hair style" default="long, silky jet-black hair styled in a loose side braid draped over one shoulder, soft wispy curtain bangs"}, luminous porcelain-fair skin, subtle rosy cheeks, naturally full pink lips, and large expressive dark brown eyes with a calm, slightly melancholic gaze looking directly into the camera. Her expression is neutral, quiet, and elegant with a gentle, introspective mood. She is wearing a {argument name="uniform" default="traditional Japanese high school uniform consisting of a tailored black blazer, crisp white dress shirt, and a deep burgundy satin ribbon bow"}. The portrait is framed from the chest upward against a smooth light blue-gray studio backdrop with soft, even school-photography lighting, minimal shadows, and true-to-life colors. The portrait is printed on a clean white yearbook page with thin white borders separating neighboring student portraits. Japanese kanji characters are printed beneath the portrait as the student's name, creating an authentic Japanese graduation album aesthetic. Adjacent student portraits are partially visible on both sides, reinforcing the official class yearbook layout. Style: ultra-realistic, Japanese school graduation album photography, minimalist composition, authentic yearbook design, soft natural skin tones, high detail, DSLR quality, shallow depth of field, sharp facial focus, subtle cinematic realism, 8K resolution.How to use
- Copy the complete original prompt, including any parameters.
- Replace the subject, text and composition with your own requirements.
- Use a compatible external tool; check its current access conditions and review the result.
Before you start
- Check whether a reference image is required. A compatible model label does not mean this example was generated with that model.
- Keep names, figures and visible text accurate; results can vary between model versions.
