Wan 2.1 VACE Video Edit

POST/v1/run

Wan 2.1 Vace 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/2.1/vace/video-edit.

Default: alibaba/wan/2.1/vace/video-edit

stringpromptrequired

Prompt to edit the video.

Optional<array<string>>images

URLs of the input images to use as a reference for the generation.

Default:

Optional<string>video

URL of the input video.

Optional<string>resolution

Resolution of the edited video.

Allowed values: auto, 240p, 360p, 480p, 720p

Default: auto

Optional<string>video_type

The type of video you're editing. Use 'general' for most videos, and 'human' for videos emphasizing human subjects and motions. The default value 'auto' means the model will guess based on the first frame of the video.

Allowed values: auto, general, human

Default: auto

Optional<string>aspect_ratio

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

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/2.1/vace/video-edit",
  "prompt": "replace him with a large anthropomorphic polar bear",
  "video": "https://static.sandbase.ai/examples/alibaba/wan/2.1/vace/video-edit/input_video_0.mp4",
  "aspect_ratio": "21:9"
}'

# 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/2.1/vace/video-edit",
  "status": "running",
  "outputs": []
}