Skip to content

Wan 2.7 Edit Video

POST/v1/run

Alibaba Wan 2.7 video editing model.

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/wan/2.7/edit-video.

Default: alibaba/wan/2.7/edit-video

stringpromptrequired

The editing instruction describing what changes to make.

Default:

stringvideorequired

The URL of the input video to edit.

Optional<array<string>>images

Reference images to guide the video editing.

Optional<string>audio_setting

Audio handling. 'auto': model decides whether to regenerate audio. 'origin': preserve original audio from input video.

Allowed values: auto, origin

Default: auto

Optional<integer>duration

Output video duration in seconds. 0 means match input video duration. When set (2-10), truncates from the start.

Allowed values: 0, 2, 3, 4, 5, 6, 7, 8, 9, 10

Default: 0

Optional<string>resolution

The resolution of the output video.

Allowed values: 720p, 1080p

Default: 720p

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: edit-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async