Submits an image edit request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.
Time-to-live in seconds for the job result after completion. Defaults to 3600 (1 hour). After expiry, the job result is automatically cleaned up.
Model identifier in format provider/model
Image file to edit. Use field name image for a single file or image[] for multiple files.
Text prompt describing the edit. Required unless type is background_removal.
Optional mask image for inpainting (transparent areas indicate regions to edit)
Type of edit operation
inpainting, outpainting, background_removal Number of images to generate
1 <= x <= 10Size of the output image
256x256, 512x512, 1024x1024, 1536x1024, 1024x1536, auto Format of the response
url, b64_json When true, stream the response via Server-Sent Events
Background type for the image
transparent, opaque, auto How closely to follow the original image
low, high Number of partial images to generate when streaming
0 <= x <= 3Quality of the output image
auto, high, medium, low, standard Output image format
png, webp, jpeg Number of inference steps
Seed for reproducible editing
Compression level (0-100%)
0 <= x <= 100What to avoid in the edit
User identifier for tracking
Fallback models to try if primary model fails
Job accepted for processing
Response returned when creating or polling an async job
Unique identifier for the async job
The status of an async job
pending, processing, completed, failed When the job was created
When the job result expires and will be cleaned up
When the job completed (successfully or with failure)
HTTP status code of the completed operation
The result of the completed operation (shape depends on the request type)
Error response from Bifrost