GET

/v1/schemas/fal/image/fal-ai/leffa/virtual-tryon

Accept:

kind inputactivity imagehash 3f099a44…extracted Aug 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `e657ce0586e7681dfedbc25bf61a24fa4cbea12a8bc08526622183fe1aecc0d2` { "fetchedAt": 1786338105, "extractorVersion": "1", "verifiedAt": null }

Request body

9 properties · 3 required · 0 $defs

property	type	description	constraints
garment_type*	enum	The type of the garment used for virtual try-on.	upper_body \| lower_body \| dresses
human_image_url*	string	Url for the human image.
garment_image_url*	string	Url to the garment image.
output_format	enum	The format of the generated image.	jpeg \| png · default: "png"
guidance_scale	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your input when generating the image.	0 ≤ n ≤ 20 · default: 2.5
sync_mode	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	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, and images flagged as unsafe are returned as black images.	default: true
seed	integer	The same seed and the same input given to the same version of the model will output the same image every time.	nullable
num_inference_steps	integer	The number of inference steps to perform.	1 ≤ n ≤ 50 · default: 50

Validate a payload

before you spend tokens

shell

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