GET

/v1/schemas/fal/image/fal-ai%2Ffast-lightning-sdxl%2Finpainting

kind inputactivity imagehash 3b81821cextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

15 properties · 3 required · 2 $defs
propertytypedescriptionconstraints
prompt*stringThe prompt to use for generating the image. Be as descriptive as possible for best results.
image_url*stringThe URL of the image to use as a starting point for the generation.
mask_url*stringThe URL of the mask to use for inpainting.
seedinteger The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time. nullable
num_inference_stepsenumThe number of inference steps to perform.1 | 2 | 4 | 8 · default: 4
num_imagesintegerThe number of images to generate.1 ≤ n ≤ 8 · default: 1
request_idstringAn id bound to a request, can be used with response to identify the request itself.default: ""
image_sizeImageSize | enumThe size of the generated image.default: "square_hd"
safety_checker_versionenumThe version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.v1 | v2 · default: "v1"
expand_promptbooleanIf set to true, the prompt will be expanded with additional prompts.default: false
formatenumThe format of the generated image.jpeg | png · default: "jpeg"
strengthnumberdetermines how much the generated image resembles the initial image0.01 ≤ n ≤ 1 · default: 0.95
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled.default: true
embeddingsEmbedding[]The list of embeddings to use.default: []
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.default: false

Validate a payload

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