GET

/v1/schemas/fal/video/fal-ai/kling-video/v2.5-turbo/standard/image-to-video

Accept:

kind inputactivity videohash 3a2d0026…extracted Oct 14, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `64383251990a39918b76d784690bf9990c602790dfe7fc351aab969be1e84efc` { "fetchedAt": 1791954060, "extractorVersion": "1", "verifiedAt": null }

Request body

6 properties · 2 required · 0 $defs

property	type	description	constraints
image_url*	string	URL of the image to be used for the video
prompt*	string		length ≤ 2500
cfg_scale	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.	0 ≤ n ≤ 1 · default: 0.5
duration	enum	The duration of the generated video in seconds	5 \| 10 · default: "5"
negative_prompt	string		length ≤ 2500 · default: "blur, distort, and low quality"
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/kling-video/v2.5-turbo/standard/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}