Qwen Image 3 Edit
/v1/runAlibaba Qwen Image 3 image editing model with support for up to three reference images.
Request body
Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.
Model identifier. Set to alibaba/qwen-image-3/edit.
Default: alibaba/qwen-image-3/edit
The editing instruction describing what changes to make.
Default: 用途:precise-object-edit。图像1是唯一编辑目标。这是中国高中数学试卷批改真实性测试。
严格保留原图的木桌、相机视角、纸张轮廓与阴影,以及全部黑色印刷文字、题号、公式、图形和版式;禁止重绘、改写、移动或删除原试卷内容。只新增以下红色教师签字笔笔迹:
1. 在试卷右上角写“112/150”并用红笔圈住。
2. 在四个部分标题旁依次写“45/60”“15/20”“10/20”“42/70”。
3. 仅在第3、14、25题题号旁画红色叉号;仅在第1、13、21题题号旁画红色勾号。
4. 在第25题旁写“计算错误”,在第22题旁写“过程不完整”。
红笔必须像中国高中教师真实批卷:自然手写、轻微倾斜、压感和墨迹浓淡变化,位置准确且不遮挡题干。不要添加学生答案、手、人物、文具、印章、水印或其他内容。除指定红笔内容外,画面保持不变。
List of input image URLs for editing. Supports 1 to 3 images.
The aspect ratio of the generated image.
Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
Default: 3:4
The format of the generated image.
Allowed values: jpeg, png
Default: png
Random seed for reproducibility (0-2147483647).
Default: 20260724
Response Schema
The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.
Error message if the task failed. Empty on success.
Unique identifier for the generation task.
Model ID used for the prediction.
Array of generated content. Empty when status is not completed.
Status of the task: pending, running, completed, failed, or timeout.
Allowed values: pending, running, completed, failed, timeout
Model capabilities
Capabilities declared by the model registry.
Default: image-editing
Execution mode declared by the model registry.
Default: async

