GET

/v1/schemas/fal/image/fal-ai/fooocus

Accept:

kind inputactivity imagehash 5356efcc…extracted Nov 11, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `6fd64d71fb886672b3c9f237056bb6b3426e786215f41d323683b6c92db8fa56` { "fetchedAt": 1794373202, "extractorVersion": "2", "verifiedAt": null }

Request body

22 properties · 0 required · 1 $defs

property	type	description	constraints
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
mask_image_url	string	The image to use as a mask for the generated image.	nullable
aspect_ratio	string	The size of the generated image. You can choose between some presets or custom height and width that must be multiples of 8.	default: "1024x1024"
performance	enum	You can choose Speed or Quality	Speed \| Quality \| Extreme Speed \| Lightning · default: "Extreme Speed"
control_type	enum	The type of image control	ImagePrompt \| PyraCanny \| CPDS \| FaceSwap · default: "PyraCanny"
loras	LoraWeight[]	The LoRAs to use for the image generation. You can use up to 5 LoRAs and they will be merged together to generate the final image.	default: [{"path":"https://huggingface.co…
enable_safety_checker	boolean	If set to false, the safety checker will be disabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.	default: true
num_images	integer	Number of images to generate in one request	1 ≤ n ≤ 4 · default: 1
refiner_model	enum	Refiner (SDXL or SD 1.5)	None \| realisticVisionV60B1_v51VAE.saf… · default: "None"
inpaint_image_url	string	The image to use as a reference for inpainting.	nullable
refiner_switch	number	Use 0.4 for SD1.5 realistic models; 0.667 for SD1.5 anime models 0.8 for XL-refiners; or any value for switching two SDXL models.	0 ≤ n ≤ 1 · default: 0.8
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
prompt	string	The prompt to use for generating the image. Be as descriptive as possible for best results.	default: ""
control_image_weight	number	The strength of the control image. Use it to control how much the generated image should look like the control image.	0 ≤ n ≤ 2 · default: 1
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: ""
output_format	enum	The format of the generated image.	png \| jpeg \| webp · default: "jpeg"
styles	enum[]	The style to use.	default: ["Fooocus V2","Fooocus Enhance",…
control_image_stop_at	number	The stop at value of the control image. Use it to control how much the generated image should look like the control image.	0 ≤ n ≤ 1 · default: 1
mixing_image_prompt_and_inpaint	boolean		default: false
sharpness	number	The sharpness of the generated image. Use it to control how sharp the generated image should be. Higher value means image and texture are sharper.	0 ≤ n ≤ 30 · default: 2
control_image_url	string	The image to use as a reference for the generated image.	nullable
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.	1 ≤ n ≤ 30 · default: 4

Types

1 $defs

LoraWeightobject

path*	string	URL or the path to the LoRA weights.
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: 0.1

Validate a payload

before you spend tokens

shell

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