GET
/v1/schemas/fal/video/alibaba/wan-3.0-prime/text-to-video
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace1ecdbf05c0c2d03ca4212fd9fed6589c078bdacf02e14c3b5bda13304872310b{
"fetchedAt": 1788843629,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
9 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | Text prompt for the generated video. | length ≥ 1 · length ≤ 20000 |
| resolution | enum | Output video resolution tier. | 480p | 720p | 1080p · default: "1080p" |
| enable_prompt_expansion | boolean | Enable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality. | default: true |
| aspect_ratio | enum | Output aspect ratio, or adaptive selection. | adaptive | 16:9 | 4:3 | 1:1 | 3:4 | 9:16 · default: "adaptive" |
| enable_thinking | boolean | Enable enhanced reasoning before generation. | default: false |
| duration | integer | Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media. | 2 ≤ n ≤ 30 · nullable |
| audio | boolean | Include generated audio. | default: true |
| seed | integer | 0 ≤ n ≤ 2147483647 · nullable | |
| enable_safety_checker | boolean | Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked. | default: true |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"alibaba/wan-3.0-prime/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}