GET
/v1/schemas/fal/video/blackforestlabs/flux-3/image-to-video/draft
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source tracecd8c42daef02994139d6569e05819cac89c4221984769bb0e6f93820bb81022a{
"fetchedAt": 1785992534,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
6 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL or data URI of the opening keyframe image. | |
| prompt* | string | The text prompt describing the draft video. | |
| safety_tolerance | integer | The safety tolerance level for the generated video. 0 is the strictest and 4 is the most permissive. | 0 ≤ n ≤ 4 · default: 2 |
| aspect_ratio | enum | Aspect ratio of the generated draft. `auto` lets the model choose. | auto | 21:9 | 2:1 | 16:9 | 4:3 | 1:1 · +2 more · default: "auto" |
| generate_audio | boolean | Whether to generate audio for the draft video. | default: true |
| duration | enum | Draft duration in whole seconds from 5 through 20, or `auto`. | auto | 5 | 6 | 7 | 8 | 9 · +11 more · default: "auto" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"blackforestlabs/flux-3/image-to-video/draft","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}