Original document
GPT Image 2 · en
A lifelike first-person perspective photograph, set in a minimalist bedroom with soft nighttime lighting, as if the viewer is standing in front of a full-length mirror gazing at their own reflection. In the foreground, long, dark hair falls from the top and sides of the image, partially obscuring the viewer's vision; a hand is raised near the left side of the face, as if touching the cheek or hair. In the mirror's reflection, a person with {argument name="hair color" default="Dark brown"} A young woman with long, straight hair is positioned in the center of the image, wearing a loose-fitting ivory or off-white long-sleeved nightgown with delicate tiny floral patterns and wide sleeves. She poses shyly, her hands supporting her chin, elbows tucked in, creating a soft, intimate, and slightly bashful atmosphere. Her face is hidden or obscured, creating a sense of anonymous self-portrait. A mirror with a simple white frame sits on a white dressing table. The background reflected in the mirror is a neatly arranged warm beige bedroom, containing a slightly messy bed with white sheets, a small wooden bedside table or low shelf, a warm-light table lamp with a square white lampshade, and two small decorative items beside the lamp. To the right of the dressing table are two transparent skincare or cosmetic bottles and a small round white container. It employs warm ambient lighting, creamy neutral tones, shallow depth of field, soft realism, smartphone photography composition, comfortable Japanese apartment aesthetics, and a casual home atmosphere, while retaining subtle imperfections rather than studio-quality retouching.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.
