GET
/v1/schemas/fal/video/fal-ai/scail-2
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace9c5286a99795c8f27f55efac680f0a4ec17ffa5f49b3b153e3d72ee3fad8289b{
"fetchedAt": 1791522002,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
12 properties · 3 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The prompt describing the final video to generate. | |
| video_url* | string | URL of the driving (motion) video. The subject can be a human, multiple humans, or an animal. | |
| image_url* | string | URL of the reference character image. The character in this image is animated (or used to replace a subject) according to the driving video. | |
| mode | enum | `animation` animates the reference character with the driving motion. `replacement` replaces the driving subject with the reference character while keeping the original scene. | animation | replacement · default: "animation" |
| guidance_scale | number | Classifier-free guidance scale. Controls prompt adherence versus creativity. | 1 ≤ n ≤ 10 · default: 5 |
| shift | number | Flow-matching noise schedule shift. 3.0 is recommended for the 512p tier. | 1 ≤ n ≤ 10 · default: 3 |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
| driving_type | enum | Driving signal for animation mode. `end_to_end` (default) drives directly from the SAM3-masked driving video and is the recommended, most robust path. `pose` renders an explicit NLF/DWPose skeleton from the driving video (more control for challenging inputs). | end_to_end | pose · default: "end_to_end" |
| seed | integer | Random seed. Leave empty for a random seed. The seed used is returned in the response. | nullable |
| num_inference_steps | integer | Number of diffusion sampling steps. Higher improves quality but is slower. | 2 ≤ n ≤ 50 · default: 40 |
| resolution | enum | Output resolution. 512p outputs 896x512 (landscape) or 512x896 (portrait); 704p outputs 1280x704 or 704x1280. Orientation is chosen automatically from the reference image aspect ratio. | 512p | 704p · default: "512p" |
| subject_type | enum | Type of subject in the driving video. `animal` switches the SAM3 detection prompt to non-human subjects. | human | animal · default: "human" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/scail-2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}