GET

/v1/schemas/fal/video/fal-ai/kandinsky5-pro/image-to-video

Accept:

kind inputactivity videohash 5223edde…extracted Oct 14, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `7babb9bc6abf0edbbcbdcb36af454e894f18ca2a6043e4af5bc188a3b4111800` { "fetchedAt": 1791954060, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 2 required · 0 $defs

property	type	description	constraints
image_url*	string	The URL of the image to use as a reference for the video generation.
prompt*	string	The prompt to generate the video from.
seed	integer	The seed to use for generation. If not provided, a random seed will be used.	nullable
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
resolution	enum	Video resolution: 512p or 1024p.	512P \| 1024P · default: "512P"
num_inference_steps	integer		1 ≤ n ≤ 40 · default: 28
acceleration	enum	Acceleration level for faster generation.	none \| regular · nullable
duration	const	Video duration.	"5s" · default: "5s"

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/kandinsky5-pro/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}