Skip to content

Qwen Image 2 Pro Edit

POST/v1/run

Alibaba Qwen Image 2 Pro image editing model with multi-reference support and configurable output format.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to alibaba/qwen-image-2/pro/edit.

Default: alibaba/qwen-image-2/pro/edit

stringpromptrequired

The editing instruction describing what changes to make.

Default:

array<string>imagesrequired

List of input image URLs for editing. Up to 4 images.

Optional<string>aspect_ratio

The aspect ratio of the generated image.

Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21

Optional<integer>seed

Random seed for reproducible results.

Optional<string>output_format

The format of the generated image.

Allowed values: jpeg, png

Default: jpeg

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-editing

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async