alibaba/wan/motion
Wan Motion by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runalibaba/wan/motionInput Schema
6 parameters · 2 required · 4 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of the reference image (provides the character appearance). |
prompt | string | Required | Optional text prompt to guide the generation. · Default: "" |
seed | integer | Optional | Random seed for reproducibility. |
video | string | Optional | URL of the driving video (provides the motion). |
adapt_motion | boolean | Optional | Adapts the driving video's motion to match the reference image's body proportions. Recommended when the driving video subject and reference image have different body shapes or sizes. · Default: true |
enhance_identity | boolean | Optional | Enhances identity preservation by preprocessing the reference image with Flux Kontext Edit before animation. Produces more faithful face and appearance transfer at the cost of slightly longer processing time. · Default: false |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "alibaba/wan/motion",
"image": "https://static.sandbase.ai/examples/alibaba/wan/motion/input_image_0.jpg",
"video": "https://static.sandbase.ai/examples/alibaba/wan/motion/input_video_1.mp4",
"prompt": "woman dancing",
"adapt_motion": true,
"enhance_identity": false
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Wan Motion
Wan Motion transfers or directs movement in existing visual material, combining Wan video transformation with motion control, style change, lip synchronization, and effects. Its emphasis is not simply generating a new clip, but reshaping how a supplied subject performs while retaining enough source context for continuity.
Use it when the creative goal starts with an existing character or clip and calls for a new performance, synchronized mouth movement, controlled action, or a different visual treatment. State the motion target and timing clearly, then describe which identity, framing, and environmental qualities must survive the transformation.
Highlights
- Directed motion transfer. Applies a new action or movement pattern to source-led visual content.
- Lip-synchronized performance. Coordinates mouth movement with spoken timing for character or presenter footage.
- Identity-aware transformation. Preserves recognizable subject traits while changing performance or style.
- Effect-integrated editing. Combines controlled motion with visual treatment and scene-level effects in one transformed sequence.
Pricing
| Billing component | Price |
|---|---|
| Generated video | $0.060 per second |
| Enhanced identity, when enabled | +$0.080 per request |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For image-conditioned generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"image": "https://example.com/start-frame.png",
"prompt": "woman dancing",
"video": "https://example.com/source.mp4"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | alibaba/wan/motion |
| Inputs | adapt_motion, enhance_identity, image, prompt, seed, video |
| Required inputs | prompt, image |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
Related Models
alibaba/wan/2.1/flf-to-video— Compare this concrete local family route.alibaba/wan/2.1/image-to-video— Compare this concrete local family route.alibaba/wan/2.1/image-to-video/lora— Compare this concrete local family route.

