Wan 2.2 Fun Control

POST/v1/run

Wan 2.2 Fun Control is Alibaba's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

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/2.2/fun-control.

Default: alibaba/wan/2.2/fun-control

stringpromptrequired

The prompt to generate the video.

Optional<integer>seed

The seed for the random number generator.

Optional<integer>fps

The fps to generate. Only used when match_input_fps is False.

Range: 4 to 60

Default: 16

Optional<string>control_video_url

The URL of the control video to use as a reference for the video generation.

Optional<string>preprocess_type

The type of preprocess to apply to the video. Only used when preprocess_video is True.

Allowed values: depth, pose

Default: depth

Optional<boolean>preprocess_video

Whether to preprocess the video. If True, the video will be preprocessed to depth or pose.

Default: false

Optional<string>reference_image_url

The URL of the reference image to use as a reference for the video generation.

Optional<boolean>match_input_fps

Whether to match the fps in the input video.

Default: true

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: video-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/wan/2.2/fun-control",
  "prompt": "A woman wearing a lavender floral dress spins around in a circle."
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "alibaba/wan/2.2/fun-control",
  "status": "running",
  "outputs": []
}