EMO: Generate high-quality portrait video based on portrait images and human voice audio.

General Introduction

Yummy Portrait EMO is a high-quality portrait dynamic video generation tool provided by Hundred Refine (Model Studio), a big model service platform of AliCloud. The tool is based on portrait images and human voice audio files to generate realistic portrait dynamic video. Joyful Portrait EMO contains two independent models: "Joyful Portrait EMO-detect" and "Joyful Portrait EMO", which are used for character image compliance detection and character video generation respectively. Users can quickly generate high-quality character portrait videos that comply with the specifications through simple API calls, which are suitable for a variety of application scenarios, such as virtual anchors, digital people and so on.

Experience it for free in the Tongyi App. Formal commercialization is available through API calls or self-deployment on the Ali Bailian platform.

Function List

• Character Image Compliance Testing: Use the "EMO-detect" model to detect whether the input image conforms to the specification.
• Character Video Generation: Generate dynamic videos based on portrait images and vocal audio files using the "EMO Portrait" model.
• Various styles to choose from: Supports a wide range of movement style intensities such as lively, moderate, and calm.
• API call: Provides an easy-to-use API interface for developers to integrate.
• stand-alone deployment: Support model-independent deployment for high concurrency requirements.

Using Help

Installation and Configuration

1. Open Service: First of all, you need to open the Joyful Portrait EMO service on the AliCloud platform and get the API Key.
2. Get API Key: Log in to your AliCloud account and enter the big model service platform Hundred Refine to get the API Key.

Procedure for use

1. Calling the image detection model::
   • The "EMO-detect" model is used to detect whether the input portrait image conforms to the specification.
   • API call example:

    import requests
   url = "https://api.aliyun.com/emo-detect"
   headers = {"Authorization": "Bearer YOUR_API_KEY"}
   data = {"image": "base64_encoded_image"}
   response = requests.post(url, headers=headers, json=data)
   print(response.json())
   

2. Calling the video generation model::
   • Using the "Yummy Portrait EMO" model, input the detected portrait picture and vocal audio file to generate motion video.
   • API call example:

    import requests
   url = "https://api.aliyun.com/emo"
   headers = {"Authorization": "Bearer YOUR_API_KEY"}
   data = {
   "image": "base64_encoded_image",
   
   "style_level": "active"
   }
   response = requests.post(url, headers=headers, json=data)
   print(response.json())
   

stand-alone deployment

1. Purchase of resources: Purchase exclusive instance resources on the AliCloud platform.
2. Deployment models: Deploy the models "Joyful Portrait EMO-detect-deployment" and "Joyful Portrait EMO-deployment" respectively.
3. Invoke the deployment model::
   • Call the "EMO-detect-deployment" model for image detection.
   • Call the "EMO-deployment" model for video generation.

Tariffs and Stream Restrictions

caveat

• Tariffs and Stream Restrictions: Payment is based on usage, please refer to AliCloud's official documentation for specific tariffs.
• concurrency limit: Depending on the purchased arithmetic unit, different numbers of concurrent tasks are supported.

The layman's guide to getting started with AI

Help you learn how to utilize AI tools at a low cost and from a zero base.AI, like office software, is an essential skill for everyone. Mastering AI will give you an edge in your job search and half the effort in your future work and studies.

View Details>