Generate image with P-Image Edit
Pruna AI P-Image Edit — an optimised Qwen-based image editing model taking up to 3 reference images. Fast multi-image editing for composition, style transfer, and object manipulation. Refer to inputs as “image 1”, “image 2” in the prompt.
Asynchronous. Returns a job id (the image is not in this response). Poll GET /v1/images/{id} until status is succeeded — the generated image URLs are in that response’s images array (each { url, position }).
Authorizations
API key as a bearer token: Authorization: Bearer bpx_live_xxx
Body
Text instruction describing the desired edit or composition.
Reference images to edit or compose (1-3). Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads.
3Output aspect ratio. Defaults to matching the first reference image.
match_input_image, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 Number of images to generate. This model returns a single image per request.
1 <= x <= 1Seed for reproducible generation. Omit for random.