GET

/v1/schemas/fal/video/fal-ai/void-video-inpainting

kind inputactivity videohash 325504cc…extracted Jul 6, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
cc95f1db1cfef80df4f3cf3c782c297d44bdaba3f98e43b5df70c469e2b3b756
{
  "fetchedAt": 1783330412,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

12 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringText description of the desired background after object removal.
video_url*stringURL of the input video containing the object to remove.
num_framesintegerTemporal window size for inference. The backend snaps this to the nearest CogVideoX-safe value that works with temporal compression and patching. Valid outputs are 69, 77, 85, ..., 197.1 ≤ n ≤ 197 · default: 85
quad_mask_video_urlstringURL of a mask video for the removal target. For best results this should be a VOID-style quadmask video with 4 grayscale values: 0=object to remove, 63=overlap, 127=affected region, 255=background to keep. A simple binary mask (0=remove, 255=keep) also works. …default: ""
enable_safety_checkerbooleanEnable content safety checking on the output.default: true
guidance_scalenumberClassifier-free guidance scale.0 ≤ n ≤ 20 · default: 1
negative_promptstringNegative prompt to guide generation away from undesired outputs.default: "The video is not of a high qual…
enable_pass2_refinementbooleanRun VOID Pass 2 warped-noise refinement after Pass 1. This is slower but can improve temporal consistency on longer clips.default: false
mask_promptstringText description of what should be masked in the input video, such as the object or person to remove. Used to generate a temporary mask video with SAM-3 when `quad_mask_video_url` is not provided.nullable
seedintegerRandom seed for reproducibility.nullable
num_inference_stepsintegerNumber of denoising steps. Higher values improve quality but increase latency.1 ≤ n ≤ 50 · default: 30
strengthnumberDenoising strength. 1.0 means full denoising.0 ≤ n ≤ 1 · default: 1

Validate a payload

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