GET

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

Accept:

kind inputactivity videohash bf76300c…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `61d9a6dde7a9e457d52e46f159c48f645803f3b7fd5251d7a11f92cc322ead37` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 2 required · 0 $defs

property	type	description	constraints
prompt*	string	The prompt to generate the video from.	length ≤ 1000
image_url*	string	URL of the image input.
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
aspect_ratio	enum	The aspect ratio of the video to generate.	16:9 \| 9:16 · default: "16:9"
i2v_stability	boolean	Turning on I2V Stability reduces hallucination but also reduces motion.	default: false
seed	integer	The seed to use for generating the video.	nullable
resolution	const	The resolution of the video to generate.	"720p" · default: "720p"
num_frames	const	The number of frames to generate.	129 · default: 129

Validate a payload

before you spend tokens

shell

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