GET

/v1/schemas/fal/video/fal-ai/vidu/q3/image-to-video

Accept:

kind inputactivity videohash d54f84f1…extracted Oct 23, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `0da65003b361a5398d649abd9da6c57e77db9b105c57e6191c5da7752e066e85` { "fetchedAt": 1792731610, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 1 required · 0 $defs

property	type	description	constraints
image_url*	string	URL or base64 image to use as the starting frame
end_image_url	string	URL of the image to use as the ending frame. When provided, generates a transition video between start and end frames.	nullable
prompt	string	Text prompt for video generation, max 2000 characters	length ≤ 2000 · default: ""
resolution	enum	Output video resolution. Note: 360p is not available when end_image_url is provided.	360p \| 540p \| 720p \| 1080p · default: "720p"
audio	boolean	Whether to use direct audio-video generation. When true, outputs video with sound (including dialogue and sound effects).	default: true
duration	integer	Duration of the video in seconds (1-16 for Q3 models)	1 ≤ n ≤ 16 · default: 5
seed	integer	Random seed for reproducibility. If None, a random seed is chosen.	nullable
enable_safety_checker	boolean	Enable safety checks; disabling requires authorization.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/vidu/q3/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}