LivePortrait image detection API - Alibaba Cloud Model Studio

The LivePortrait-detect model verifies that input portrait images meet the specifications required by the LivePortrait model. This document describes how to call the API for this model's image detection feature.

Important

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

Model overview

Model	Description
liveportrait-detect	liveportrait-detect is a specialized image detection model used to check whether an input image meets the portrait image specifications required by the liveportrait model.

HTTP

Feature description

This model detects whether an input image meets the portrait image specifications required for LivePortrait video generation.

Prerequisites

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

Input limitations

Supported image formats: JPEG, JPG, PNG, BMP, and WebP.
The image file must be smaller than 10 MB, have an aspect ratio of 2 or less, and have a maximum edge length of 4096 pixels.
Images must be uploaded using HTTP links. Local file paths are not supported.

Task submission

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

Request parameters

Field	Type	Parameter passing	Required	Description	Example
Content-Type	String	Header	Yes	The request type. Set this 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 call. Set this to liveportrait-detect.	liveportrait-detect
input.image_url	String	Body	Yes	The URL of the image to check. The image file must be smaller than 10 MB, have an aspect ratio of 2 or less, and a maximum edge length of 4096 pixels. Supported formats: JPEG, JPG, PNG, BMP, and WebP. Note File uploads support only HTTP or HTTPS links, not local file paths.	"image_url": "http://a/a.jpg"

Response parameters

Field	Type	Description	Example
output.pass	Bool	The check result for the submitted image.	"pass":true/false
output.message	String	The message that describes the check result for the submitted image.	"message":No human face detected.
request_id	String	The unique ID of the request.	7574ee8f-38a3-4b1e-9280-11c33ab46e51

Failure reason

output.message	Description
No human face detected	No human face was detected. This can happen if the face is too small, in profile, or obstructed.

Sample request

curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/image2video/face-detect' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "liveportrait-detect",
  "input": {
      "image_url":"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250911/ynhjrg/p874909.png"
  }
}'

Sample response (passed)

{
    "output": {
        "pass": true,
        "message": ""
    },
    "usage": {
        "image_count": 1
    },
    "request_id": "a92e2ffd-9263-44ba-92c5-xxxxxx"
}

Sample response (failed)

{
    "output": {
        "pass": false,
        "message": "No human face detected."
    },
    "usage": {
        "image_count": 1
    },
    "request_id": "c56f62df-724e-9c19-96bd-xxxxxx"
}

Sample response (error)

{
    "code": "InvalidParameter.UnsupportedFileFormat",
    "message": "Input files format not supported.",
    "request_id": "788b30fe-05f6-999f-a0b1-xxxxxx"
}

Error codes

For information about common error codes, see Error messages.