GET
/v1/schemas/fal/video/fal-ai/wan/v2.7/reference-to-video
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source traced1d6161ba754c82e71d39267b4cb5d9508c98877b6dd444d1e1dfdd9371916cf{
"fetchedAt": 1786338105,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
10 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | Text prompt describing the desired video. Max 5000 characters. | length ≥ 1 |
| reference_image_urls | string[] | Reference image URLs for character/object appearance. Pass multiple images for multi-subject generation. Max 20 MB each. | nullable |
| seed | integer | Random seed for reproducibility (0-2147483647). | nullable |
| reference_video_urls | string[] | Reference video URLs for character/object appearance and motion. Pass multiple videos for multi-subject generation. Max 100 MB each. | nullable |
| enable_safety_checker | boolean | Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked. | default: true |
| duration | enum | Output video duration in seconds (2-10). | 2 | 3 | 4 | 5 | 6 | 7 · +3 more · default: 5 |
| multi_shots | boolean | When true, enables intelligent multi-shot segmentation. When false (default), generates a single continuous shot. | default: false |
| aspect_ratio | enum | Aspect ratio of the generated video. | 16:9 | 9:16 | 1:1 | 4:3 | 3:4 · default: "16:9" |
| negative_prompt | string | Content to avoid in the video. Max 500 characters. | nullable |
| resolution | enum | Output video resolution tier. | 720p | 1080p · default: "1080p" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/wan/v2.7/reference-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}