Qwen-Image-Layered generates images as semantically separated layers for subsequent composition and editing. It is designed for workflows that need more control than a single flattened image.
Key strengths
- Layer-separated output
- Editable composition
- Semantic element isolation
- Qwen image ecosystem
Use cases
- Graphic design handoff
- Poster composition
- Asset extraction
- Layer-based editing
WaveSpeed's wavespeed/qwen-image-layered is a state-of-the-art text-to-image generation model. It produces highly detailed, photorealistic and stylized imagery from natural-language prompts, with strong instruction following and accurate text rendering inside generated images.
Compatible with the OpenAI `/images/generations` endpoint shape, supporting prompt, size, seed, negative prompt, and resolution controls. Excellent for creative workflows, marketing assets, product visualization, and concept art at scale.
wavespeed/qwen-image-layered is fully OpenAI-compatible — drop in your existing OpenAI Python or Node SDK and switch `baseURL` to `https://api.tokenlx.ai`. TokenLX transparently routes your requests to the optimal provider endpoint while preserving streaming, function-calling, and structured-output semantics.
Performance
Compare different providers across TokenLX · All locations.
Effective Pricing
Pricing is shown by the model billing method, using per-call or per-second prices and resolution tiers.
Recent activity
Total usage per day on TokenLX (last 30 days).
Sample code & API
TokenLX normalizes requests and responses across providers. Use any OpenAI SDK or our native SDK.
import requests
headers = {
"Authorization": "Bearer sk-aihub-...",
"Content-Type": "application/json",
}
# Decompose one image into four RGBA layers
response_1 = requests.post(
"https://api.tokenlx.ai/v1/generate/image/generations",
headers=headers,
json={"model": "qwen-image-layered", "prompt": "Separate foreground and background", "files": [{"file_uri": "https://example.com/source.png", "mime_type": "image/png"}], "layeredConfig": {"numLayers": 4}},
)
print(response_1.json())Replace sk-aihubrouter-… with your key from the dashboard.
Parameter Reference
{
"data": ["url1", "url2"]
}| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model name |
| size | string | No | Output size in W*H format (e.g. 2048*2048). 3.0 series auto-recommends resolution when omitted 512*512 ~ 2048*2048（宽高比 1:8~8:1） |
| promptExtend | bool | No | Expand prompt automatically (default true) |
| seed | int | No | Random seed [0, 2147483647] (Qwen only) |
| negative_prompt | string | No | Negative prompt (≤500 chars, Qwen only) |
| watermark | bool | No | Add watermark (default false, Qwen only) |
| images | array | Editing | Input images for editing (max 3) |
| images[].file_uri | string | Editing | Image URL or base64 data URI |
| images[].mime_type | string | No | MIME type, defaults to image/png |
modelstringYessizestringNo512*512 ~ 2048*2048（宽高比 1:8~8:1）promptExtendboolNoseedintNonegative_promptstringNowatermarkboolNoimagesarrayEditingimages[].file_uristringEditingimages[].mime_typestringNo