GET

/v1/schemas/fal/video/fal-ai/pixverse/v4.5/text-to-video/fast

kind inputactivity videohash 765b986d…extracted Oct 9, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
79ece21dbbb21c67fa2e396b6adea280c1d3ca42886fd132c535c3c7a295b823
{
  "fetchedAt": 1791522002,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

7 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringText prompt for the video generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
seedinteger The same seed and the same prompt given to the same version of the model will output the same video every time. nullable
enable_safety_checkerbooleanAuthorized callers may set false to request relaxed screening.default: true
aspect_ratioenumThe aspect ratio of the generated video16:9 | 4:3 | 1:1 | 3:4 | 9:16 · default: "16:9"
resolutionenumThe resolution of the generated video360p | 540p | 720p · default: "720p"
negative_promptstringNegative prompt to be used for the generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.default: ""
styleenumThe style of the generated videoanime | 3d_animation | clay | comic | cyberpunk · nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/pixverse/v4.5/text-to-video/fast","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}