GET

/v1/schemas/fal/video/fal-ai/wan-motion

Accept:

kind inputactivity videohash 3be4e530…extracted Aug 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `0713f3d3a29bdf43c6bdb2527722c5300c1eb01172ec5d9710ce31afba64ebfc` { "fetchedAt": 1786338105, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 2 required · 0 $defs

property	type	description	constraints
video_url*	string	URL of the driving video (provides the motion).
image_url*	string	URL of the reference image (provides the character appearance).
enable_safety_checker	boolean	If set to true, input and output will be checked for safety. Disabling it requires account authorization; unauthorized requests are always checked.	default: true
seed	integer	Random seed for reproducibility.	nullable
adapt_motion	boolean	Adapts the driving video's motion to match the reference image's body proportions. Recommended when the driving video subject and reference image have different body shapes or sizes.	default: true
acceleration	enum	Acceleration level to use. 'regular' enables caching for faster generation, 'none' disables it.	none \| regular · default: "regular"
enhance_identity	boolean	Enhances identity preservation by preprocessing the reference image with Flux Kontext Edit before animation. Produces more faithful face and appearance transfer at the cost of slightly longer processing time.	default: false
prompt	string	Optional text prompt to guide the generation.	default: ""

Validate a payload

before you spend tokens

shell

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