alibaba/wan/move
Wan Move by Alibaba - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Input
Text prompt to guide the video generation.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.
This field is required.
A list of trajectories. Each trajectory list means the movement of one object.
Random seed for reproducibility. If None, a random seed is chosen.
Idle
Example output — click Run to generate your own
Production endpoint
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
POST
https://api.sandbase.ai/v1/runModel ID
alibaba/wan/move01
Input Schema
4 parameters · 2 required · 2 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped. |
prompt | string | Required | Text prompt to guide the video generation. |
seed | integer | Optional | Random seed for reproducibility. If None, a random seed is chosen. |
trajectories | array[] | Optional | A list of trajectories. Each trajectory list means the movement of one object. |
02
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
03
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/move",
"image": "https://static.sandbase.ai/examples/alibaba/wan/move/input_image_0.png",
"prompt": "In a boxing gym, the camera captures a half-body view of a single man practicing shadow boxing inside the ring. The camera sways slightly, emphasizing movement and intensity. He wears black boxing gloves, black shorts, and boxing shoes. With no opponent present, he throws a controlled straight punch into the air, his lead arm fully extended while the other hand stays tight near his face in a defensive guard. His body rotates subtly through the hips and shoulders, and his feet shift lightly across the mat to maintain balance and rhythm. Sweat highlights his muscular form as he focuses forward, fully immersed in his training. The background features blurred gym equipment and hanging heavy bags, reinforcing the sense of motion and concentration.",
"trajectories": [
[
{
"x": 334,
"y": 286,
"speed": 1
},
{
"x": 334,
"y": 322,
"speed": 1
},
{
"x": 372,
"y": 328,
"speed": 1
},
{
"x": 447,
"y": 338,
"speed": 1
},
{
"x": 518,
"y": 328,
"speed": 1
},
{
"x": 481,
"y": 283,
"speed": 1
},
{
"x": 440,
"y": 263,
"speed": 1
},
{
"x": 385,
"y": 252,
"speed": 1
},
{
"x": 347,
"y": 252,
"speed": 1
}
],
[
{
"x": 555,
"y": 262,
"speed": 1
},
{
"x": 505,
"y": 242,
"speed": 1
},
{
"x": 466,
"y": 243,
"speed": 1
},
{
"x": 440,
"y": 264,
"speed": 1
},
{
"x": 439,
"y": 287,
"speed": 1
},
{
"x": 471,
"y": 330,
"speed": 1
},
{
"x": 541,
"y": 345,
"speed": 1
},
{
"x": 572,
"y": 335,
"speed": 1
},
{
"x": 589,
"y": 303,
"speed": 1
}
]
]
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Wan Move
Wan Move brings a supplied photograph or illustration into motion, generating cinematic subject action, camera travel, and environmental response around the established frame. It is designed for image-led animation where the source should remain visually recognizable as the clip develops.
Describe the movement that begins after the source frame: subject gesture, secondary motion such as hair or fabric, camera path, depth changes, ambience, and any sound intention. It fits character moments, product showcases, landscape animation, and social clips built from finished still artwork.
Highlights
- Cinematic photo animation. Develops an approved still into a composed moving shot rather than a simple slideshow effect.
- Natural secondary motion. Animates hair, fabric, particles, reflections, and environment around the primary action.
- Source identity preservation. Keeps subjects and art direction recognizable throughout the generated movement.
- Camera-and-audio staging. Can combine directed camera behavior with optional sound for a more complete scene.
Pricing
| Billing unit | Price |
|---|---|
| Per request | $0.2 |
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": "In a boxing gym, the camera captures a half-body view of a single man practicing shadow boxing inside the ring. The camera sways slightly, emphasizing movement and intensity. He wears black boxing gloves, black shorts, and boxing shoes. With no opponent present, he throws a controlled straight punch into the air, his lead arm fully extended while the other hand stays tight near his face in a defensive guard. His body rotates subtly through the hips and shoulders, and his feet shift lightly across the mat to maintain balance and rhythm. Sweat highlights his muscular form as he focuses forward, fully immersed in his training. The background features blurred gym equipment and hanging heavy bags, reinforcing the sense of motion and concentration."
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | alibaba/wan/move |
| Inputs | image, prompt, seed, trajectories |
| 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.