Motion Transfer & Character Swap

Doc version：v1.0.0 | Last updated：2026-07-22
This platform fully supports the official Tongyi Wanxiang (Wan) video generation API. Requests and responses are transparently proxied; parameter semantics are identical to the official API.

Based on a single character image and a reference video, these models provide two character animation capabilities: "Motion Transfer" and "Character Swap" (video character replacement) — the wan2.2-animate series.

Model Capability Comparison

Model	Capability	Use Cases
`wan2.2-animate-move`	Motion Transfer: transfers the motions and facial expressions from the reference video onto the character in the image, bringing the still image to life	Dance replication, complex body movement replication, film/TV performance replication; can serve as a low-cost alternative to motion capture
`wan2.2-animate-mix`	Character Swap: replaces the main character in the video with the character from the image, while preserving the original video's scene, lighting, and color tone (the original video's motions, expressions, and environment are unchanged)	Derivative creation, film/TV post-production, and other character replacement scenarios

Both models share the same submission endpoint, distinguished by the model field; both offer two service modes (parameters.mode):

Mode	Description
`wan-std` Standard mode	Fast generation and high cost-effectiveness, suitable for quick previews and basic animation scenarios
`wan-pro` Professional mode	Smoother animation, better image quality, and better results, with correspondingly higher processing time and cost

Create Task

POST https://platform.dataeyes.ai/ali/api/v1/services/aigc/image2video/video-synthesis

Request Headers

Parameter	Type	Required	Default	Description
`Content-Type`	string	Yes	application/json	Data exchange format
`Authorization`	string	Yes		Authentication, `Bearer {API_KEY}`

The X-DashScope-Async: enable header required by the official API is automatically added by the platform — you do not need to include it; including it is also compatible.

Request Body

Parameter	Type	Required	Default	Description
`model`	string	Yes		`wan2.2-animate-move` (Motion Transfer) or `wan2.2-animate-mix` (Character Swap)
`input`	object	Yes		Input parameter object
`input.image_url`	string	Yes		Publicly accessible HTTP/HTTPS URL of the character image. If the URL contains Chinese or other non-ASCII characters, it must be URL-encoded first
`input.video_url`	string	Yes		Publicly accessible HTTP/HTTPS URL of the reference video. Must likewise be URL-encoded. The official recommendation is to use a high-resolution, high-frame-rate reference video for better output quality
`input.watermark`	boolean	No	false	Whether to add an AI-generated watermark in the bottom-right corner of the video. `true` to add, `false` to omit
`parameters`	object	Yes		Parameter object
`parameters.mode`	string	Yes		Service mode: `wan-std` (Standard) / `wan-pro` (Professional); see the mode comparison table above for the differences
`parameters.check_image`	boolean	No	true	Whether to inspect the input image before processing. `true` to inspect; `false` to skip inspection and process directly

Input Material Requirements

The requirements are identical for both the move and mix models:

Item	Image `image_url`	Video `video_url`
Format	JPG, JPEG, PNG, BMP, WEBP	MP4, AVI, MOV
Dimensions	Width and height both within [200, 4096] pixels, aspect ratio 1:3 ~ 3:1	Width and height both within [200, 2048] pixels, aspect ratio 1:3 ~ 3:1
Size	≤ 5 MB	≤ 200 MB
Duration	—	2 ~ 30 seconds

Character and quality optimization tips (official):

Keep the character's frame proportion in the input image similar to that in the reference video;

Keep the character's body proportions consistent between the image and the video;

Use high-definition materials — avoid blurry images and low-frame-rate videos to ensure accurate detail recognition.

Request Example: Motion Transfer (Standard mode)

curl --request POST \
  --url 'https://platform.dataeyes.ai/ali/api/v1/services/aigc/image2video/video-synthesis' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "wan2.2-animate-move",
    "input": {
      "image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg",
      "video_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4"
    },
    "parameters": {
      "mode": "wan-std"
    }
  }'

Request Example: Character Swap (Professional mode)

curl --request POST \
  --url 'https://platform.dataeyes.ai/ali/api/v1/services/aigc/image2video/video-synthesis' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "wan2.2-animate-mix",
    "input": {
      "image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg",
      "video_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4"
    },
    "parameters": {
      "mode": "wan-pro"
    }
  }'

Response Example

{
  "output": {
    "task_status": "PENDING",
    "task_id": "0385dc79-5ff8-4d82-bcb6-xxxxxx"
  },
  "request_id": "4909100c-7b5a-9f92-bfe5-xxxxxx"
}

Field	Type	Description
`output.task_id`	string	Task ID used for polling, valid for 24 hours
`output.task_status`	string	Task status, `PENDING` on successful creation
`request_id`	string	Unique request identifier, used for tracing and troubleshooting

Results and Usage

After the task succeeds, the query endpoint returns the video URL at output.results.video_url (MP4, H.264 encoded, valid for 24 hours); the usage field is the basis for billing:

{
  "output": {
    "task_status": "SUCCEEDED",
    "results": {
      "video_url": "https://.../xxxxx.mp4?Expires=xxx"
    }
  },
  "usage": {
    "video_duration": 5.2,
    "video_ratio": "standard"
  }
}

Field	Type	Description
`usage.video_duration`	float	Duration of the successfully generated video, in seconds
`usage.video_ratio`	string	Service mode identifier: `standard` (corresponds to `wan-std`) / `pro` (corresponds to `wan-pro`)

Billing notes: Input is not billed; billing is based on the number of seconds of successfully generated output video. Professional mode (pro) has a higher unit price than Standard mode (standard). Failed calls incur no charges.

Query Task

After creating a task, poll for its status and results using task_id:

GET https://platform.dataeyes.ai/ali/api/v1/tasks/{task_id}

For the detailed response structure, task status enum, and polling recommendations, see 09-Query-Task.

06-Motion-Transfer-and-Character-Swap

Motion Transfer & Character Swap#

Model Capability Comparison#

Create Task#

Request Headers#

Request Body#

Input Material Requirements#

Request Example: Motion Transfer (Standard mode)#

Request Example: Character Swap (Professional mode)#

Response Example#

Results and Usage#

Query Task#