GET

/v1/schemas/fal/video/fal-ai%2Fkandinsky5-pro%2Ftext-to-video

kind inputactivity videohash 25c8135bextracted Jul 22, 2026version currentsource upstream spec ↗

Request body

7 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringThe text prompt to guide video generation.
accelerationenumAcceleration level for faster generation.none | regular · nullable
durationconstThe length of the video to generate."5s" · default: "5s"
seedintegerThe seed to use for generation. If not provided, a random seed will be used.nullable
aspect_ratioenumAspect ratio of the generated video. One of (3:2, 1:1, 2:3).3:2 | 1:1 | 2:3 · default: "3:2"
num_inference_stepsintegerThe number of inference steps.1 ≤ n ≤ 50 · default: 28
resolutionenumVideo resolution: 512p or 1024p.512P | 1024P · default: "512P"

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/kandinsky5-pro/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}