Use GPT Image 2.6 Flare for prompt-based creation or reference-guided image editing.
The demo and examples were generated with GPT Image 2.6 Flare. README visuals are illustrative artwork.
Resolution pricing
PNG, JPEG, WebP, and SVG. Each task returns one image.
GIF animation
Fixed price per GIF, regardless of size or frame settings.
Playground Examples
A premium studio product photograph of unbranded burnt-orange over-ear headphones resting on a pale limestone cube, a curved brushed-aluminum panel behind them and deep indigo shadows, precise seams and tactile ear cushions, soft directional light, elegant balanced arrangement. Wide landscape 16:9 composition. No text, letters, logos, or watermark.
A cinematic architectural photograph of a small brutalist reading pavilion overlooking a misty pine valley, board-formed concrete, warm oak shelving visible through a large glass opening, a shallow reflecting pool, one rust-colored chair, quiet late-afternoon light and realistic material texture. Wide landscape 16:9 composition. No people, text, letters, logos, or watermark.
An intricate gouache illustration of a tiny fox cartographer in a floating observatory above a sea of clouds, brass telescope, folded blank maps, warm glowing windows, blue twilight sky and a slender crescent moon, handcrafted paper texture, coherent miniature architecture, copper and indigo palette. Wide landscape 16:9 composition. No text, letters, logos, or watermark.
Similar Models
High-fidelity image generation and reference-guided editing with photorealistic detail, typography, and flexible framing.
Create expressive images with Midjourney 8.2, 8.1, 7, or Niji 7, with controls for composition, stylization, and repeating patterns.
ByteDance image generation and editing for cinematic visuals, product shots, precise local edits, and reference-guided creative work.
Model overview
Create still images, SVG vectors, or animated GIFs from a written brief or reference images. Choose resolution and framing for still images and SVG, or pixel size and timing for GIF animation.
Describe the subject, material, background, lighting, and camera angle. Product concepts, still lifes, and campaign imagery are useful starting points for exploring your visual direction.
For still images and SVG, choose 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9 with a separate resolution tier. For GIF, use auto or explicit pixel dimensions divisible by 16, then set the frame count and frame duration. Describe the motion and desired loop in your prompt.
The image-edit workflow accepts 1–16 reference images. Explain the role of each reference and specify which subject details, colors, or layout elements should remain.
Model characteristics
Use Text to Image when starting from a prompt. Select Image Edit when source or reference images should guide the result.
List the desired changes and the elements to preserve. Give each reference a clear purpose instead of relying on the upload alone.
Both workflows support PNG, JPEG, WebP, SVG vectors, and GIF animation. GIF uses size, frame_count, and frame_duration_ms in place of aspect ratio and resolution.
Submit a task with your API key, retain data.task_id, and poll the shared task endpoint or supply a top-level webhook for completion.
FAQ
Text to Image needs a nonblank prompt. Image Edit also requires 1–16 reference images.
Upload JPG, JPEG, PNG, or WebP images. API requests use public HTTP(S) URLs.
For still images and SVG, frame options are 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9 and resolution tiers are 1K, 2K, 4K. Defaults are 1:1 and 1K. GIF uses auto or widthxheight pixel size instead, with each dimension divisible by 16.
Select GIF in either workflow and describe the motion. For reference-guided animation, use Image Edit and upload source images. Set size, choose 2–64 frames, and set 20–2000 milliseconds per frame. Defaults are auto size, 9 frames, and 200 milliseconds.
Poll the task endpoint until it succeeds and read data.output_urls, or use the top-level webhook callback.
