GET
/v1/schemas/fal/video/fal-ai/cosmos-predict-2.5/distilled/text-to-video
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source tracedc2fab14e0604ec319248af12204b66bfd4f7d53d48c2f9cadc269f71e1bb82a{
"fetchedAt": 1791522002,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
9 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The text prompt describing the video to generate. | |
| num_inference_steps | integer | Number of denoising steps. Distilled model works well with fewer steps. | 1 ≤ n ≤ 20 · default: 10 |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. | default: false |
| negative_prompt | string | A negative prompt to guide generation away from undesired content. | default: "The video captures a series of … |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
| video_output_type | enum | The format of the output video. | X264 (.mp4) | VP9 (.webm) | PRORES4444 (.mov) | GIF (.gif) · default: "X264 (.mp4)" |
| video_quality | enum | The quality of the output video. | low | medium | high | maximum · default: "high" |
| seed | integer | Random seed for reproducible generation. | nullable |
| num_frames | integer | Number of frames to generate. Must be between 9 and 93. | 9 ≤ n ≤ 93 · default: 93 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/cosmos-predict-2.5/distilled/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}