GET
/v1/schemas/fal/video/fal-ai%2Fkling-video%2Fo3%2Fpro%2Freference-to-video
Accept:
Request body
10 properties · 0 required · 2 $defs| property | type | description | constraints |
|---|---|---|---|
| elements | KlingV3ComboElementInput[] | Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2. | nullable |
| start_image_url | string | Image to use as the first frame of the video. | nullable |
| prompt | string | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. | length ≤ 2500 · nullable |
| aspect_ratio | enum | The aspect ratio of the generated video frame. | 16:9 | 9:16 | 1:1 · default: "16:9" |
| shot_type | enum | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. | customize | intelligent · default: "customize" |
| image_urls | string[] | Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video. | nullable |
| duration | enum | Video duration in seconds (3-15s). | 3 | 4 | 5 | 6 | 7 | 8 · +7 more · default: "5" |
| multi_prompt | KlingV3MultiPromptElement[] | List of prompts for multi-shot video generation. | nullable |
| generate_audio | boolean | Whether to generate native audio for the video. | default: false |
| end_image_url | string | Image to use as the last frame of the video. | nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/kling-video/o3/pro/reference-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}