Image Editing (Image-to-Image)

Novel AI image-to-image is called through the async image task entry: POST /v1/images/async/generations, carrying one reference image in the image field (an http/https image URL or a base64 data URI) to enter image-to-image / editing mode — for sketch-to-final, style transfer, redraw and other anime image workflows.

The interface is async: on success it returns an image.task object (with task_id); poll the Query Result endpoint with the returned task ID until status becomes completed to fetch the final image.

Single reference image

Novel AI image-to-image accepts exactly one reference image per request, passed in the image field as a publicly reachable http/https image URL or a base64 data URI (data:image/...;base64,...). Local files can be converted to base64 and passed directly — no upload needed. The generation count n supports 1-4.

curl -X POST "https://www.omwai.xyz/v1/images/async/generations" \  -H "Content-Type: application/json" \  -d '{    "model": "nai-diffusion-4-5-curated",    "prompt": "保留人物主体，将背景改为樱花飘落的校园，动漫风格",    "image": "https://example.com/source.png",    "size": "1024x1024",    "n": 1  }'

{
  "id": "task_01J8ABCDEFGHIJKLMNOPQRST",
  "task_id": "task_01J8ABCDEFGHIJKLMNOPQRST",
  "object": "image.task",
  "model": "nai-diffusion-4-5-curated",
  "status": "queued",
  "progress": "0%",
  "created_at": 1788256630,
  "completed_at": 1788256720
}

{
  "code": "invalid_request",
  "message": "string"
}

{
  "code": "string",
  "message": "string"
}