Live APIQwen Image Tools

Qwen Layered

qwen-layered

Decompose a source image into editable semantic layers for design, compositing, and asset-production workflows.

View request Docs

Model overview

Endpoint: /api/v1/images/generations
Credit cost: 10 credits / layer
Typical latency: 30-90 sec
Input and output: Image and instruction → Layer images

Capabilities

1-8 semantic layers
Prompt-guided separation
Transparent assets
Seed control

Request parameters

Parameter	Type	Requirement	Description
model	string	Required	Model identifier. Default: `qwen-layered`
image	string	Required	Public source image URL.
prompt	string	Required	Description of the desired layer separation.
num_layers	integer	Optional	Number of layers from 1 to 8. Default: `4`
size	string	Optional	Output pixel dimensions. Default: `1024*1024`

Request example

curl https://qwenapi.org/api/v1/images/generations \
  -H "Authorization: Bearer $QWEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen-layered",
  "image": "https://example.com/poster.png",
  "prompt": "Separate the subject, typography, foreground objects, and background",
  "num_layers": 4,
  "size": "1024*1024"
}'

The generation endpoint is asynchronous. Poll GET /api/v1/tasks/ with the same Bearer key.