Real-time Live Streaming Digital Human

实时直播数字人 bilibili video

News

fastest and cpu real-time model released! try demo_mini.py! More demo on PC、 web、 android&IOS will be released soon！

All checkpoint files are moved to baiduNetDisk

Training

Details on the render model training can be found here. Audio Model training Details can be found here.

Video Example

demo.mp4

Overview

This project is a real-time live streaming digital human powered by few-shot learning. It is designed to run smoothly on all 30 and 40 series graphics cards, ensuring a seamless and interactive live streaming experience.

Key Features

Real-time Performance: The digital human can interact in real-time with 25+ fps for common NVIDIA 30 and 40 series GPUs
Few-shot Learning: The system is capable of learning from a few examples to generate realistic responses.

Usage

Create Environment and Unzip the Model File

First, navigate to the checkpoint directory and unzip the model file:

conda create -n dh_live python=3.12
conda activate dh_live
pip install torch --index-url https://download.pytorch.org/whl/cu124
pip install -r requirements.txt
cd checkpoint

on Linux

cat render.pth.gz.001 render.pth.gz.002 > render.pth.gz
gzip -d -c render.pth.gz > render.pth

on Windows, use zip software such as 7zip/WinRAR to unzip checkpoint file.

Prepare Your Video

Next, prepare your video using the data_preparation script. Replace YOUR_VIDEO_PATH with the path to your video:

python data_preparation.py YOUR_VIDEO_PATH

The result (video_info) will be stored in the ./video_data directory.

Run with Audio File

Run the demo script with an audio file. Make sure the audio file is in .wav format with a sample rate of 16kHz and 16-bit single channel. Replace video_data/test with the path to your video_info file, video_data/audio0.wav with the path to your audio file, and 1.mp4 with the desired output video path:

python demo.py video_data/test video_data/audio0.wav 1.mp4

Real-Time Run with Microphone

For real-time operation using a microphone, simply run the following command:

python demo_avatar.py

Acknowledgements

We would like to thank the contributors of Wav2Lip, DINet, LiveSpeechPortrait repositories, for their open research and contributions.

License

This project is licensed under the MIT License.

Contact

For any questions or suggestions, please contact us at [kleinlee1@outlook.com].

kleinlee/DH_live