GET

/v1/schemas/fal/image/fal-ai/qwen-image-layered/lora

Accept:

kind inputactivity imagehash 51714d64…extracted Aug 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `ee8299686c1efb68f0a715a5815f5a8316de118b1323aa2c6b73eaead0107bc3` { "fetchedAt": 1786338105, "extractorVersion": "1", "verifiedAt": null }

Request body

12 properties · 1 required · 1 $defs

property	type	description	constraints
image_url*	string	The URL of the input image.
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
output_format	enum	The format of the generated image.	png \| webp · default: "png"
num_inference_steps	integer	The number of inference steps to perform.	1 ≤ n ≤ 50 · default: 28
seed	integer	The same seed and the same prompt given to the same version of the model will output the same image every time.	nullable
negative_prompt	string	The negative prompt to generate an image from.	default: ""
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
loras	LoRAInput[]	List of LoRA weights to apply (maximum 3).	default: []
guidance_scale	number	The guidance scale to use for the image generation.	1 ≤ n ≤ 20 · default: 5
num_layers	integer	The number of layers to generate.	1 ≤ n ≤ 10 · default: 4
prompt	string	A caption for the input image.	nullable
acceleration	enum	The acceleration level to use.	none \| regular \| high · default: "regular"

Types

1 $defs

LoRAInputobject

LoRA weight configuration.

path*	string	URL, HuggingFace repo ID (owner/repo) to lora weights.
scale	number	Scale factor for LoRA application (0.0 to 4.0).	0 ≤ n ≤ 4 · default: 1

Validate a payload

before you spend tokens

shell

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