GET

/v1/schemas/fal/image/fal-ai/stepx-edit2

kind inputactivity imagehash 52e91b8b…extracted Jul 6, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
1a9f21d18439112bb9b7db87c38195b1285cf6f36fd642d28f7fe304046ee292
{
  "fetchedAt": 1783331098,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

11 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
image_url*stringThe image URL to generate an image from. Needs to match the dimensions of the mask.
prompt*stringThe prompt to generate an image from.
enable_reflection_modebooleanEnable reflection mode. Reviews outputs, corrects unintended changes, and determines when editing is complete.default: true
num_inference_stepsintegerThe number of inference steps to perform. Recommended: 50.1 ≤ n ≤ 100 · default: 50
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: "jpeg"
negative_promptstringThe 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: ""
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled.default: true
guidance_scalenumberThe true CFG scale. Controls how closely the model follows the prompt.0 ≤ n ≤ 20 · default: 6
enable_thinking_modebooleanEnable thinking mode. Uses multimodal language model knowledge to interpret abstract editing instructions.default: true
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/stepx-edit2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}