GET
/v1/schemas/fal/video/fal-ai%2Fid-v2v
Accept:
Request body
12 properties · 3 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The prompt describing the restyled video to generate. | |
| video_url* | string | URL of the source video whose motion and framing drive the generation. | |
| image_url* | string | URL of the restyled first frame. The video is regenerated in this frame's identity/style. | |
| num_frames | integer | Maximum number of output frames. Capped at the source video's frame count. | 17 ≤ n ≤ 241 · default: 81 |
| seed | integer | Random seed for reproducibility. The same seed is used for every clip of a multi-clip generation. | nullable |
| keyframes | Keyframe[] | Optional restyled keyframes pinned at specific output frame indices to anchor identity over long videos. | items ≤ 5 |
| enable_safety_checker | boolean | Enable safety checking of inputs and outputs. | default: true |
| resolution | enum | Output resolution tier. Orientation follows the source video (720p is 1280x720 or 720x1280; 480p is 832x480 or 480x832). | 480p | 720p · default: "720p" |
| segmentation_prompt | string | Text prompt for SAM-3 subject segmentation. The segmented subject's pixels condition the generation; the rest of the frame is regenerated freely. | length ≤ 100 · default: "person" |
| num_inference_steps | integer | Number of diffusion sampling steps per clip. Higher improves quality but is slower. | 2 ≤ n ≤ 40 · default: 30 |
| vace_scale | number | VACE conditioning scale. Controls how strongly the source video's structure constrains the generation. | 0 ≤ n ≤ 2 · default: 1 |
| guidance_scale | number | Classifier-free guidance scale. Controls prompt adherence versus creativity. | 1 ≤ n ≤ 10 · default: 5 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/id-v2v","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}