AnimateAnyone action template generation API - Alibaba Cloud Model Studio

The action template generation modelof AnimateAnyone extracts movements from a motion video and generates an action template for video generation. This topic describes how to call the action template generation API.

Important

This document applies only to the China (Beijing) region. To use the model, you must use an API key for the China (Beijing) region.

Model overview

Model	Description
animate-anyone-template-gen2	Extracts character movements from a motion video to generate a character action template.

Examples

Correct examples

Examples of videos that meet the requirements for creating action templates

Note

The person in the uploaded video must be fully visible, with a clear face and no obscured body parts.
The person must appear from the first frame of the video. The action must be continuous and captured in a single take. Split videos with scene changes into multiple segments.
For best results, the person should face the camera in the first frame. Avoid actions such as excessive bending, squatting, or crouching.

Incorrect examples

Curled postures and self-occlusion

Multiple people in the frame

Blurry person

Person too small

(Unclear face)

Person too large

(Person not fully visible)

身体遮挡@3x

多人物@3x

f3e2df6643d44db7a7d65d4571609bff_3 (1)

人物过小@3x

人物过大@3x

Note

To ensure the quality of the generated template, make sure that no frame in the uploaded video contains any of the preceding errors.
If the first frame of the video contains any of the preceding errors, the submitted task may fail and be aborted.

Important

Make sure that the source of the uploaded video file complies with relevant laws and regulations.
The audio of the generated action template is the same as the audio in the uploaded video file. If you do not want to use this audio, or if you have not obtained a license for it, such as for background music, remove the audio from the video file before you upload it.

HTTP

Feature description

Generates a character action template. This template can be used as an input for the AnimateAnyone video generation API to generate a character action video.

Prerequisites

You have activated Alibaba Cloud Model Studio and created an API key, see Get an API key.

Input limits

Video format: MP4, AVI, or MOV.
The video file size cannot exceed 200 MB.
The length of each side of the video must be between 200 and 2,048 pixels. The video frame rate must be 24 frames per second (fps) or higher. The video must be encoded in H.264 or H.265.
The video duration must be from 2 seconds to 60 seconds.
The aspect ratio of the video must be between 1:3 and 3:1.
Only HTTP URLs are supported. Local file paths are not supported.

Step 1: Create a task and obtain the task ID

POST https://dashscope.aliyuncs.com/api/v1/services/aigc/image2video/aa-template-generation/

Note

This API call is time-consuming. Therefore, the task is submitted asynchronously.
After you submit the task, the system returns a task ID. You can then use the task ID to query the task status and result.

Request parameters

Field	Type	Location	Required	Description	Example
Content-Type	String	Header	Yes	Request body format.	application/json
Authorization	String	Header	Yes	Your API key with the `Bearer` prefix.	Bearer d1**2a
X-DashScope-Async	String	Header	Yes	Set to `enable` for asynchronous task submission.	enable
model	String	Body	Yes	Model to use.	animate-anyone-template-gen2
input.video_url	String	Body	No	URL of the video to generate an action template from. The video file size cannot exceed 200 MB. The length of each side of the video must be between 200 and 2,048 pixels. The video frame rate must be 24 fps or higher. The video must be encoded in H.264 or H.265. The video duration must be from 2 seconds to 60 seconds. The aspect ratio of the video must be between 1:3 and 3:1. Supported video formats: MP4, AVI, and MOV. Note File uploads support only HTTP or HTTPS links. Local file paths are not supported.	http://aaa/bbb.mp4

Response parameters

Field	Type	Description	Example
output.task_id	String	ID of the submitted asynchronous task. Use this ID to query the task result.	a8532587-fa8c-4ef8-82be-0c46b17950d1
output.task_status	String	Task status after submission.	"PENDING"
request_id	String	Unique request identifier.	7574ee8f-38a3-4b1e-9280-11c33ab46e51

Request example

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2video/aa-template-generation/' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "animate-anyone-template-gen2",
    "input": {
        "video_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241210/cwjmsz/1.mp4"
    }
  }'

Response example

{
    "output": {
	"task_id": "a8532587-fa8c-4ef8-82be-xxxxxx", 
    	"task_status": "PENDING"
    },
    "request_id": "7574ee8f-38a3-4b1e-9280-xxxxxx"
}

Step 2: Query the result by task ID

GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}

Request parameters

Field	Type	Location	Required	Description	Example
Authorization	String	Header	Yes	Your API key with the `Bearer` prefix.	Bearer d1**2a
task_id	String	URL Path	Yes	ID of the task to query.	a8532587-fa8c-4ef8-82be-0c46b17950d1

Response parameters

Field	Type	Description	Example
output.task_id	String	ID of the queried task.	a8532587-fa8c-4ef8-82be-0c46b17950d1
output.task_status	String	Status of the queried task.	Task statuses: PENDING RUNNING SUCCEEDED FAILED UNKNOWN: The task does not exist or its status is unknown.
output.template_id	String	Action template ID returned by the platform. Use this ID as input for the AnimateAnyone video generation API. The template_id is permission-verified. The Alibaba Cloud account using the template must be the same as the account that generated it.	AACT.xxx.xxx-xxx.xxx
usage.video_duration	Float	Duration of the generated template, in seconds.	"video_duration": 10.23
usage.video_ratio	String	Aspect ratio type of the generated template. Value: `standard`.	"video_ratio": "standard"
request_id	String	Unique request identifier.	7574ee8f-38a3-4b1e-9280-11c33ab46e51

Request example

curl -X GET \
--header 'Authorization: Bearer <YOUR_API_KEY>' \
https://dashscope.aliyuncs.com/api/v1/tasks/<YOUR_TASK_ID>

Response example

{
    "request_id": "7574ee8f-38a3-4b1e-9280-11c33ab46e51",
    "output": {
        "task_id": "a8532587-fa8c-4ef8-82be-0c46b17950d1",
        "task_status": "SUCCEEDED",
        "template_id": "AACT.xxx.xxx-xxx.xxx"
    },
    "usage": {
        "video_duration": 10.23,
        "video_ratio": "standard"
    }
}

Error response example

{
    "request_id": "7574ee8f-38a3-4b1e-9280-11c33ab46e51",
    "output": {
        "task_id": "a8532587-fa8c-4ef8-82be-0c46b17950d1",
        "task_status": "FAILED",
        "code": "xxx",
        "message": "xxxxxx"
    }
}

What to do next

Use the action template for AnimateAnyone video generation.

Error codes

For common status codes, see Error messages.