Qwen Image · Image
Qwen Image · Introduction
Qwen image generation and image editing through the qwen gateway. Select the concrete model with the request body model field. Text-to-image: qwen-image / qwen-image-plus / qwen-image-2.0 / qwen-image-2.0-pro / qwen-image-max / qwen-image-plus-2026-01-09, plus Wan wan2.7-image / wan2.7-image-pro (4K pro) / wan2.5-t2i-preview; image editing: qwen-image-edit-plus / wan2.5-i2i-preview (image edit / multi-image fusion). All models are async to callers: the submit call returns a taskId; poll by taskId until status = succeeded / failed.
How to call
- Submit:
POST /api/cqt/generator/qwen, returns a taskId. - Query:
GET /api/cqt/info/qwen?id=taskId, poll until status = succeeded.
Capability map
POSTText to ImageNEW
Generate images from text with Qwen image models.
POSTImage EditingNEW
Edit one or more input images using a text instruction (wan2.5-i2i-preview supports multi-image fusion).
Common Errors
| Code | msg | Meaning | How to fix |
|---|---|---|---|
| 451 | input_moderation / output_moderation | Prompt, input image, or generated result was flagged | Edit the prompt or replace the input image, then retry |
| 400 | invalid_request | Invalid parameter or unsupported value | Check model / aspectRatio / numImages / imageUrls fields |
| 500 | failed / timeout | Task failed or timed out; data.errorMsg usually contains details | Adjust based on the error and retry; contact support if it persists |
Errors are returned as a bizCode, e.g. bizCode=451, msg=prompt_unsafe.
Tip: after saving your API Key via Authorize, every capability page supports "Try it".