GET
/v1/schemas/fal/video/fal-ai%2Fdavinci-magihuman
Accept:
Request body
9 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL of the reference image for image-to-video generation. | |
| prompt* | string | Text prompt describing the desired video content. | length ≥ 1 |
| enable_safety_checker | boolean | If enabled, runs safety checks on the prompt and input image. | default: true |
| duration | integer | Duration of the generated video in seconds. | 1 ≤ n ≤ 30 · default: 5 |
| num_inference_steps | integer | Number of denoising steps. Defaults to 8 for 256p and 32 for 540p/720p/1080p (base + SR). | 1 ≤ n ≤ 50 · nullable |
| audio_url | string | Optional URL of the driving audio for lipsync mode. If omitted, audio is generated from the prompt. | nullable |
| guidance_scale | number | Classifier-free guidance scale. | 0 ≤ n ≤ 20 · default: 5 |
| resolution | enum | Output resolution. '256p' uses the official base-model 448x256 path. '1080p' uses the official base + 1080p super-resolution pipeline. '540p' and '720p' reuse that sharper 1080p SR path and downsample to the requested output size. | 256p | 540p | 720p | 1080p · default: "256p" |
| seed | integer | Random seed for reproducibility. | nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/davinci-magihuman","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}