GET

/v1/schemas/fal/image/fal-ai%2Fflux-kontext-lora%2Finpaint

kind inputactivity imagehash 49889427extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

14 properties · 4 required · 1 $defs
propertytypedescriptionconstraints
mask_url*stringThe URL of the mask for inpainting.
reference_image_url*stringThe URL of the reference image for inpainting.
image_url*stringThe URL of the image to be inpainted.
prompt*stringThe prompt for the image to image task.
num_imagesintegerThe number of images to generate.1 ≤ n ≤ 4 · default: 1
output_formatenumThe format of the generated image.jpeg | png · default: "png"
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
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled.default: true
num_inference_stepsintegerThe number of inference steps to perform.10 ≤ n ≤ 50 · default: 30
lorasLoraWeight[]The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image.default: []
strengthnumberThe strength of the initial image. Higher strength values are better for this model.0.01 ≤ n ≤ 1 · default: 0.88
guidance_scalenumberThe 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: 2.5
seedinteger The same seed and the same prompt given to the same version of the model will output the same image every time. nullable
accelerationenumThe speed of the generation. The higher the speed, the faster the generation.none | regular | high · default: "none"

Validate a payload

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