GET

/v1/schemas/fal/image/fal-ai/qwen-image-edit/inpaint

kind inputactivity imagehash fea8ecc9…extracted Aug 8, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
db84cf6b28ddf63d518df580d1e874c0c1f9c47fc316a3d4efded1dc30b494cd
{
  "fetchedAt": 1786165357,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

14 properties · 3 required · 1 $defs
propertytypedescriptionconstraints
image_url*stringThe URL of the image to edit.
mask_url*stringThe URL of the mask for inpainting
prompt*stringThe prompt to generate the image with
strengthnumberStrength of noising process for inpainting0.01 ≤ n ≤ 1 · default: 0.93
enable_safety_checkerbooleanIf 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
negative_promptstringThe negative prompt for the generationdefault: " "
num_imagesintegerThe number of images to generate.1 ≤ n ≤ 4 · default: 1
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: 4
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
seedinteger The same seed and the same prompt given to the same version of the model will output the same image every time. nullable
output_formatenumThe format of the generated image.jpeg | png · default: "png"
num_inference_stepsintegerThe number of inference steps to perform.2 ≤ n ≤ 50 · default: 30
image_sizeImageSize | enumThe size of the generated image.nullable
accelerationenumAcceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.none | regular | high · default: "regular"

Types

1 $defs

ImageSizeobject

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

Validate a payload

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