GET
/v1/schemas/fal/video/fal-ai/kandinsky5-pro/text-to-video
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace9669498ece1690179ad93d0030646fcb1613df7d0557d8e190d603a79f26e994{
"fetchedAt": 1791522002,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
8 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The text prompt to guide video generation. | |
| num_inference_steps | integer | The number of inference steps. | 1 ≤ n ≤ 50 · default: 28 |
| aspect_ratio | enum | Aspect ratio of the generated video. One of (3:2, 1:1, 2:3). | 3:2 | 1:1 | 2:3 · default: "3:2" |
| acceleration | enum | Acceleration level for faster generation. | none | regular · nullable |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
| duration | const | The length of the video to generate. | "5s" · default: "5s" |
| resolution | enum | Video resolution: 512p or 1024p. | 512P | 1024P · default: "512P" |
| seed | integer | The seed to use for generation. If not provided, a random seed will be used. | nullable |
Validate a payload
before you spend tokensshell
$ 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", …}]}