Videos Images
Sign in
Lonely Night Dining Portrait

Lonely Night Dining Portrait

views192
likes17
comments0
shares0
bookmarks0
quotes0
Create a quiet, cinematic photorealistic portrait of a young woman sitting alone at a round dining table in a dim apartment at night. The subject is {argument name="character description" default="a slim young East Asian woman with pale skin, shoulder-length straight black hair with wispy bangs, and round wire-frame glasses"}. She wears {argument name="outfit" default="soft pale blue satin pajamas with white piping, loose long sleeves, matching long pants, and fluffy white animal-face slippers"}. She sits centered on a wooden chair, knees together under the table, leaning forward with one elbow on the tabletop and her cheek resting lightly on her hand, looking off to the right with a distant, thoughtful, slightly melancholic expression. On the table there is exactly 1 visible object: a small clear glass filled with dark iced tea or cola placed near her in the center foreground. The setting is a modern dining room with dark gray floor-to-ceiling curtains filling the background, a black round table with a thick edge, wooden chairs partially cropped at the left and right edges, a low cabinet on the left with a small plant, a dark doorway on the right, wood flooring, and the bottom of a large ceiling pendant lamp barely visible at the top edge. Use {argument name="lighting" default="soft moody nighttime interior lighting with a cool blue cast, warm rim light from the right, gentle reflections on the glossy floor, and shallow depth of field"}. Compose as a vertical 2:3 image, eye-level camera, medium-full body framing, realistic lens compression, subdued colors, high detail in hair, fabric sheen, glass reflections, and curtain folds. Avoid text, logos, extra people, extra tableware, or exaggerated anime styling; keep it natural photorealistic with a subtle Japanese lifestyle magazine mood.

✨ 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.