Videos Images
Sign in
Moody Restaurant AI Beauty Portrait

Moody Restaurant AI Beauty Portrait

views6,800
likes45
comments1
shares1
bookmarks39
quotes0
Create a hyper-realistic vertical smartphone photo of a calm {argument name="character ethnicity" default="young East Asian woman"} sitting at a dimly lit upscale restaurant table at night, viewed from slightly above chest level in a candid social-media style. She has {argument name="hair color and style" default="long messy black hair with wispy bangs and loose face-framing strands"}, soft glossy makeup, large reflective eyes, and a serene slightly melancholic expression while resting her right cheek on her right fist and looking directly into the camera. She wears a {argument name="top" default="pale pink spaghetti-strap camisole"} and delicate bracelets on her right wrist, including pearl beads, gold chain details, and small black clover charms. Her left hand holds a {argument name="phone case" default="bright yellow phone case covered in black doodle-style signatures"} at the lower left edge of the frame, as if taking or checking a selfie. The restaurant background contains exactly 8 notable visible objects: 1 dark green curtain on the left hanging from a metal rod, 1 textured gray concrete wall, 1 strip of exposed brick on the far right, 2 warm gold table lamps, 2 empty wine glasses on white tablecloths, and 1 small orange flower arrangement in the rear right. Use moody cinematic mixed lighting with warm candlelamp glow from the tables and a cool violet-blue cast across her face and skin, shallow depth of field, realistic skin texture, subtle film grain, natural lens distortion, and high detail. Frame her from mid-torso upward, centered slightly right, with intimate restaurant ambience, no text overlay, no watermark, no extra fingers, and no distorted jewelry or glassware.

✨ 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.