GET
/v1/schemas/fal/video/fal-ai/pixverse/v5.5/image-to-video
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source tracea919790e489f04800ef1c4b08b6e61344908ee8deadda7fdf5f5c5b7b0bb5af2{
"fetchedAt": 1791522002,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
11 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL of the image to use as the first frame | |
| prompt* | string | Text prompt for the video generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap. | |
| generate_multi_clip_switch | boolean | Enable multi-clip generation with dynamic camera changes | default: false |
| negative_prompt | string | Negative prompt to be used for the generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap. | default: "" |
| generate_audio_switch | boolean | Enable audio generation (BGM, SFX, dialogue) | default: false |
| style | enum | The style of the generated video | anime | 3d_animation | clay | comic | cyberpunk · nullable |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
| duration | enum | The duration of the generated video in seconds. Longer durations cost more. 1080p videos are limited to 5 or 8 seconds | 5 | 8 | 10 · default: "5" |
| resolution | enum | The resolution of the generated video | 360p | 540p | 720p | 1080p · default: "720p" |
| seed | integer | The same seed and the same prompt given to the same version of the model will output the same video every time. | nullable |
| thinking_type | enum | Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision | enabled | disabled | auto · nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/pixverse/v5.5/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}