GET

/v1/schemas/fal/video/fal-ai/krea-wan-14b/text-to-video

Accept:

kind inputactivity videohash 984521ca…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `9faaa9a571ef08487b7a4f0f08ee8df7a79ba938af22f1062ea37193aa335f69` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	Prompt for the video-to-video generation.
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
seed	integer	Seed for the video-to-video generation.	nullable
enable_prompt_expansion	boolean	Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.	default: false
num_frames	integer	Number of frames to generate. Must be a multiple of 12 plus 6, for example 6, 18, 30, 42, etc.	18 ≤ n ≤ 162 · default: 78

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/krea-wan-14b/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}