Appearance

Wan Ati

POST/v1/run

Wan Ati is Alibaba's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

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/ati.

Default: alibaba/wan/ati

stringpromptrequired

The text prompt to guide video generation.

stringimagerequired

URL of the input image.

Optional<string>resolution

Resolution of the generated video (480p, 580p, 720p).

Allowed values: 480p, 720p

Default: 480p

Optional<array<array>>track

Motion tracks to guide video generation. Each track is a sequence of points defining a motion trajectory. Multiple tracks can control different elements or objects in the video. Expected format: array of tracks, where each track is an array of points with 'x' and 'y' coordinates (up to 121 points per track). Points will be automatically padded to 121 if fewer are provided. Coordinates should be within the image dimensions.

Optional<integer>seed

Random seed for reproducibility. If None, a random seed is chosen.

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-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async