GET

/v1/schemas/fal/video/fal-ai/hunyuan-video

Accept:

kind inputactivity videohash d2dd122a…extracted Sep 8, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `629c4a6ecdc83b3931fa5a0744496aa2246384468164047c2ca1307967162de2` { "fetchedAt": 1788843629, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	The prompt to generate the video from.
resolution	enum	The resolution of the video to generate.	480p \| 580p \| 720p · default: "720p"
num_frames	enum	The number of frames to generate.	129 \| 85 · default: 129
aspect_ratio	enum	The aspect ratio of the video to generate.	16:9 \| 9:16 · default: "16:9"
seed	integer	The seed to use for generating the video.	nullable
pro_mode	boolean	By default, generations are done with 35 steps. Pro mode does 55 steps which results in higher quality videos but will take more time and cost 2x more billing units.	default: false
enable_safety_checker	boolean	If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked.	default: false

Validate a payload

before you spend tokens

shell

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