GET

/v1/schemas/fal/video/fal-ai%2Fbirefnet%2Fv2%2Fvideo

kind inputactivity videohash bb222ee5…extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

9 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
video_url*stringURL of the video to remove background from
operating_resolutionenumThe resolution to operate on. The higher the resolution, the more accurate the output will be for high res input images. The '2304x2304' option is only available for the 'General Use (Dynamic)' model.1024x1024 | 2048x2048 | 2304x2304 · default: "1024x1024"
refine_foregroundbooleanWhether to refine the foreground using the estimated maskdefault: true
modelenumModel to use for background removal. The 'General Use (Light)' model is the original model used in the BiRefNet repository. The 'General Use (Light 2K)' model is the original model used in the BiRefNet repository but trained with 2K images. The 'General Use (H…General Use (Light) | General Use (Light 2K) | General Use (Heavy) | Matting | Portrait | General Use (Dynamic) · default: "General Use (Light)"
video_write_modeenumThe write mode of the generated video.fast | balanced | small · default: "balanced"
output_maskbooleanWhether to output the mask used to remove the backgrounddefault: false
video_qualityenumThe quality of the generated video.low | medium | high | maximum · default: "high"
video_output_typeenumThe output type of the generated video.X264 (.mp4) | VP9 (.webm) | PRORES4444 (.mov) | GIF (.gif) · default: "X264 (.mp4)"
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.default: false

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/birefnet/v2/video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}