AnimateAnyone image detection API - Alibaba Cloud Model Studio

The AnimateAnyone image detection model verifies that an input character image meets the requirements for AnimateAnyone video generation. This document describes how to call the API to use the image detection feature provided by this model.

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-detect-gen2	animate-anyone-detect-gen2 is an image detection model that is used to detect whether an input image meets the character image specifications required by animate-anyone-gen2.

Examples

Examples of correct character image

Full-body shot

Half-length shot

A single person is fully visible from head to toe, and the body is not occluded.
The person is facing the camera without a large-angle side view or camera tilt.

AA_正面建议_全身@4x

A single person is fully visible from the waist up, and the body is not occluded.
The person is facing the camera without a large-angle side view or camera tilt.

AA_正面建议_半身@4x

Examples of failed character image]

Non-frontal shot

(Side view of the body and face)

Dim light

(The person is not clear)

Person occlusion

(Hands are covered by clothing, or the person is holding an object)

Complex background

Photo with multiple people

AA_错误_侧身侧脸@4x

AA_错误_光线暗淡@4x

AA_错误_手拿物品@4x

AA_错误_复杂背景@4x

Use HTTP

Feature description

This model is used to determine whether an input image meets the character image specifications for the AnimateAnyone video generation API.

Prerequisites

You have activated Alibaba Cloud Model Studio and obtained an API key. For more information, see Get an API key.

Task submission

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

Request parameters

Parameter	Type	Method	Required	Description	Example
Content-Type	String	Header	Yes	The request type. Set the value to application/json.	application/json
Authorization	String	Header	Yes	The API key. Example: Bearer d1**2a.	Bearer d1**2a
model	String	Body	Yes	The model to be invoked.	animate-anyone-detect-gen2
input.image_url	String	Body	Yes	The URL of the image to be checked. The URL must be a publicly accessible address and support the HTTP or HTTPS protocol.	"image_url": "http://a/a.jpg"

Response parameters

Parameter	Type	Description	Example
output.check_pass	Bool	The check result that corresponds to the image list submitted by the customer.	"check_pass":true/false
output.bodystyle	String	The body style. `half` indicates a half-length shot, and `full` indicates a full-body shot.	"bodystyle": half/full
output.reason	String	The reason for the check result that corresponds to the image list submitted by the customer.
request_id	String	The request ID.	7574ee8f-38a3-4b1e-9280-11c33ab46e51

Reasons for a failed detection

output.reason	Description
The input image contains no person or multiple people. Please upload an image that contains a single person.	The input image contains no person or multiple people.
The image resolution is invalid. The longest side of the image must be less than 4096 pixels, and the shortest side must be greater than 224 pixels.	The size of the uploaded image does not meet the requirements.
The pose of the detected person is invalid. Please upload another image that shows the full body and the expected orientation.	The pose of the person does not meet the requirements. (The shoulders and ankles must be visible. The person cannot be facing away from the camera or sitting. The orientation of the person cannot have a severe deviation.)
The pose of the detected face is invalid. Please upload another image that shows the full face and the expected orientation.	The face of the person does not meet the requirements. (The face must be visible. The orientation of the head cannot have a severe deviation.)

Sample request

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":"http://xxx/1.jpg"
  },
  "parameters": {
  }
}'

Sample response (passed)

{
    "output":{
        "check_pass": true,
        "reason": 'success'
    },
    "usage":{
        "image_count":1
    },
    "request_id":"c56f62df-724e-9c19-96bd-308627cf5262"
}

Sample response (failed)

{
    "output":{
        "check_pass": false,
        "reason": "no human detect"
    },
    "usage":{
        "image_count":1
    },
    "request_id":"c56f62df-724e-9c19-96bd-308627cf5262"
}

Status codes

For information about the common status codes, see Error messages.

This model also has the following specific error codes:

HTTP status code*	code	message	Description
400	InvalidParameter	Parameter required: xxx	A request parameter is missing or the format is incorrect.
400	InvalidURL	The request URL is invalid, please check the request URL is available and the request image format is one of the following types: JPEG, JPG, PNG, BMP, and WEBP.	Failed to download the input image. Check the network connection or the input format.
400	InvalidFile.Content	The input image has no human body or multi human bodies. Please upload other image with single person.	The input image contains no person or multiple people.
400	InvalidFile.Resolution	The image resolution is invalid, please make sure that the largest length of image is smaller than 4096, and the smallest length of image is larger than 224.	The size of the uploaded image does not meet the requirements.
400	InvalidFile.BodyPose	The pose of the detected person is invalid, please upload other image with whole body and expected orientation.	The pose of the person does not meet the requirements. (The shoulders and ankles must be visible. The person cannot be facing away from the camera or sitting. The orientation of the person cannot have a severe deviation.)
400	InvalidFile.FacePose	The pose of the detected face is invalid, please upload other image with whole face and expected orientation.	The face of the person does not meet the requirements. (The face must be visible. The orientation of the head cannot have a severe deviation.)