GET
/v1/schemas/fal/image/fal-ai%2Fbirefnet
Accept:
Request body
7 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL of the image to remove background from | |
| operating_resolution | enum | The resolution to operate on. The higher the resolution, the more accurate the output will be for high res input images. | 1024x1024 | 2048x2048 · default: "1024x1024" |
| output_mask | boolean | Whether to output the mask used to remove the background | default: false |
| refine_foreground | boolean | Whether to refine the foreground using the estimated mask | default: true |
| output_format | enum | The format of the output image | webp | png | gif · default: "png" |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. | default: false |
| model | enum | Model to use for background removal. The 'General Use (Light)' model is the original model used in the BiRefNet repository. The 'General Use (Heavy)' model is a slower but more accurate model. The 'Portrait' model is a model trained specifically for portrait i… | General Use (Light) | General Use (Heavy) | Portrait · default: "General Use (Light)" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/birefnet","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}