openai/gpt-image-2.5-sunburst/edit
OpenAI's GPT Image 2.5 Sunburst Edit edits one or more reference images from natural-language instructions, with five quality tiers up to 4K. Sunburst is the precision-focused GPT Image 2.5 tier that spends more time per image for extra fidelity on intricate detail.
Examples
Transform the woman into a medieval knight displaced in the modern world while preserving her exact face, posture, and overall body proportions. Replace the trench coat with elegant silver armor and a dark blue cloak, transform the coffee cup into a polished metal goblet, and add a sheathed sword at her side. Keep the subway carriage modern and realistic so the contrast feels humorous and visually striking. Cinematic realism, refined detail, interesting character contrast.
Try this prompt →
Transform the woman into a medieval knight displaced in the modern world while preserving her exact face, posture, and overall body proportions. Replace the trench coat with elegant silver armor and a dark blue cloak, transform the coffee cup into a polished metal goblet, and add a sheathed sword at her side. Keep the subway carriage modern and realistic so the contrast feels humorous and visually striking. Cinematic realism, refined detail, interesting character contrast.
Try this prompt →
Turn this watch movement photo into a premium print advertisement: add a dark navy backdrop, a subtle vignette, and the headline text "PRECISION, ENGINEERED" in elegant serif typography at the top, keep every gear and jewel exactly as shown
Try this prompt →
Transform the elegant dinner scene into a stylish underground champion’s celebration while preserving the boxer’s face, body build, hand wraps, and seated position. Add a championship belt draped over the chair, bruises and sweat details, cheering silhouettes in the background, and subtle gold confetti on the table. Keep the restaurant refined but give it a victorious post-fight energy. Cinematic sports-luxury contrast, cool and dramatic.
Try this prompt →Specs
Similar models
Prices are per render and charged from your balance only when a render succeeds. Failed renders are refunded automatically. Examples show what the model can do; your result depends on your prompt and settings.