Qwen Image Layered

60 credits/call
ae_qwen_image_layered

Split a single image into multiple editable layers for independent editing and compositing.

SegmentationImage
60 credits/call

Pricing

60 credits/call
ConditionCharge
Each call60 credits/call

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNo The same seed and the same prompt given to the same version of the model will output the same image every time. —
request_body.promptstring | unknownNoA caption for the input image.—
request_body.image_urlstringYesThe URL of the input image.—
request_body.sync_modebooleanNoIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.false
request_body.num_layersintegerNoThe number of layers to generate.4
request_body.accelerationenum (none | regular | high)NoThe acceleration level to use.regular
request_body.output_formatenum (png | webp)NoThe format of the generated image.png
request_body.guidance_scalenumberNoThe guidance scale to use for the image generation.5
request_body.negative_promptstringNoThe negative prompt to generate an image from.""
request_body.num_inference_stepsintegerNoThe number of inference steps to perform.28
request_body.enable_safety_checkerbooleanNoIf set to true, the safety checker will be enabled.true

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_qwen_image_layered' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "image_url": "https://agentearth.ai/fileserver/file/6afd7559-ffe5-4dd6-a529-093ce5922eb9.png",
      "num_layers": 4,
      "output_format": "png",
      "prompt": "separate the three cooling towers and the factory hall into distinct editable layers, blueprint line art on blue background"
    }
  }
}'
Response exampleresponse.json
JSONPartial content
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "f0ec29ba-280c-4aeb-8d2f-9dd325c9aea4"
}

This example shows part of the response. Copied content is valid JSON.