GET

/v1/schemas/fal/image/fal-ai/sdxl-controlnet-union/inpainting

Accept:

kind inputactivity imagehash 4f82626d…extracted Oct 29, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `f857cf0e40b67143f56d709908ff3c3c922ff44e2d0c3a32805c854029a6c730` { "fetchedAt": 1793250001, "extractorVersion": "1", "verifiedAt": null }

Request body

31 properties · 3 required · 3 $defs

property	type	description	constraints
image_url*	string	The URL of the image to use as a starting point for the generation.
mask_url*	string	The URL of the mask to use for inpainting.
prompt*	string	The prompt to use for generating the image. Be as descriptive as possible for best results.
segmentation_image_url	string	The URL of the control image.	nullable
num_images	integer	The number of images to generate.	1 ≤ n ≤ 8 · default: 1
depth_image_url	string	The URL of the control image.	nullable
embeddings	Embedding[]	The list of embeddings to use.	default: []
normal_image_url	string	The URL of the control image.	nullable
segmentation_preprocess	boolean	Whether to preprocess the segmentation image.	default: true
controlnet_conditioning_scale	number	The scale of the controlnet conditioning.	0 ≤ n ≤ 1 · default: 0.5
enable_prompt_expansion	boolean	If set to true, the prompt will be expanded with additional prompts.	default: false
teed_preprocess	boolean	Whether to preprocess the teed image.	default: true
safety_checker_version	enum	The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.	v1 \| v2 · default: "v1"
negative_prompt	string	The negative prompt to use.Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).	default: ""
request_id	string	An id bound to a request, can be used with response to identify the request itself.	default: ""
teed_image_url	string	The URL of the control image.	nullable
strength	number	determines how much the generated image resembles the initial image	0.01 ≤ n ≤ 1 · default: 0.95
openpose_image_url	string	The URL of the control image.	nullable
openpose_preprocess	boolean	Whether to preprocess the openpose image.	default: true
image_size	ImageSize \| enum	The size of the generated image. Leave it none to automatically infer from the control image.	nullable · default: null
depth_preprocess	boolean	Whether to preprocess the depth image.	default: true
num_inference_steps	integer	The number of inference steps to perform.	1 ≤ n ≤ 70 · default: 35
normal_preprocess	boolean	Whether to preprocess the normal image.	default: true
canny_preprocess	boolean	Whether to preprocess the canny image.	default: true
guidance_scale	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.	0 ≤ n ≤ 20 · default: 7.5
format	enum	The format of the generated image.	jpeg \| png · default: "jpeg"
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
canny_image_url	string	The URL of the control image.	nullable
loras	LoraWeight[]	The list of LoRA weights to use.	default: []
enable_safety_checker	boolean	If set to true, the safety checker will be enabled.	default: true
seed	integer	The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.	nullable

Types

3 $defs

Embeddingobject

path*	string	URL or the path to the embedding weights.
tokens	string[]	The list of tokens to use for the embedding. When omitted, tokens are generated as <s0>, <s1>, ... to match the number of vectors in the embedding file.	nullable

ImageSizeobject

height	integer	The height of the generated image.	0 < n ≤ 14142 · default: 512
width	integer	The width of the generated image.	0 < n ≤ 14142 · default: 512

LoraWeightobject

scale	number	The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model.	0 ≤ n ≤ 1 · default: 1
force	boolean	If set to true, the embedding will be forced to be used.	default: false
path*	string	URL or path to a LoRA safetensors file. Or HF model name that resolves to safetensors weights.

Validate a payload

before you spend tokens

shell

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