AnimateAnyone image detection API - Alibaba Cloud Model Studio

The image detection model of AnimateAnyone checks whether an input image is suitable for its video generation. This topic describes how to call the image detection API.

Important

This topic applies only to the China (Beijing) region. To use models, you must use an API key from the China (Beijing) region.

Model overview

Model	Description
animate-anyone-detect-gen2	Checks whether an input image is suitable for the animate-anyone-gen2 model.

Examples

Passing examples

Full-body shot

Half-body shot

A single person is visible from head to toe without obstructions.
The person faces the camera without significant turning or tilting.

Recommended full-body front view for AA

A single person is visible from the waist up without obstructions.
The person faces the camera without significant turning or tilting.

Recommended half-body front view for AA

Failing examples

Side view (Not facing forward)	Poor lighting (Person is unclear)	Obstructions (Hands covered, holding objects)	Complex background	Multiple people

HTTP

Prerequisites

Activate the service and get an API key.

Request endpoint

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

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`
model	String	Body	Yes	The model to use.	`animate-anyone-detect-gen2`
input.image_url	String	Body	Yes	URL of the image to check. The URL must be publicly accessible over HTTP or HTTPS.	`"image_url": "http://a/a.jpg"`

Response parameters

Field	Type	Description	Example
output.check_pass	Boolean	Whether the image passed the check.	`true`
output.bodystyle	String	Detected body style. Valid values: `half` (half-body shot) `full` (full-body shot).	`half`
output.reason	String	Reason for detection failure. Returned only when `check_pass` is `false`.	`The input image has no human body...`
usage.image_count	Integer	Number of images checked.	`1`
request_id	String	Unique request identifier.	`7574ee8f-38a3-4b1e-9280-11c33ab46e51`

Request example

curl --location --request POST 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2video/aa-detect' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "animate-anyone-detect-gen2",
  "input": {
      "image_url":"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20251224/pkswoc/p883941.png"
  }
}'

Successful response examples

Image passes detection

{
    "output": {
        "bodystyle": "full",
        "check_pass": true
    },
    "usage": {
        "image_count": 1
    },
    "request_id": "76df937d-6eb6-40aa-9ccf-xxxxxx"
}

Image fails detection

{
    "output":{
        "check_pass": false,
        "reason": "The input image has no human body. Upload another image that contains a single person.",
        "bodystyle": ""
    },
    "usage":{
        "image_count": 1
    },
    "request_id": "c56f62df-724e-9c19-96bd-xxxxxx"
}

Failed request example

{
    "code": "InvalidApiKey",
    "message": "No API-key provided.",
    "request_id": "7438d53d-6eb8-4596-8835-xxxxxx"
}

What to do next

Use the image for AnimateAnyone video generation.

Error codes

For a list of general status codes, see Error codes.