In this tutorial we will use the Sadtalker to bring an image or video back to life , along with lip sync.

This tutorial has 3 parts :

Part 1: Setting up the Environment

Part 2: Bring to life based on image and audio

Part 3: Bring to life based on video and audio

Check out our tutorial here : https://youtu.be/dqkM0lxrruQ

Roop : https://github.com/s0md3v/roop ===========================================  git clone https://github.com/s0md3v/roop.git cd roop  conda create --name roop python=3.10 conda activate roop  conda install -c conda-forge ffmpeg pip install -r requirements.txt  # copy expmaple files : copy face image to the roop folder copy a video (to be replaced) to the roop folder   # If you are using Windows You should also install :  1. Microsoft Visual C++ Redistributable : https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170  2. Microsoft C++ Build Tools : https://visualstudio.microsoft.com/visual-cpp-build-tools/   #Run command - no GPU : =======================  1. If you don't have Gpu card :  python run.py -----------------------------------------  2. If you have Gpu card :  pip uninstall onnxruntime onnxruntime-gpu pip install onnxruntime-gpu==1.15.1  #Run command - With GPU : python run.py --execution-provider cuda ---------------------------------------------  a. Choose your image b. CHoose your target video c. click Start

Instructions for this video: https://ko-fi.com/s/e371beb945

More relevant content in this playlist : https://www.youtube.com/playlist?list=PLdkryDe59y4bxVvpexwR6PMTHH6_vFXjA

You can find more tutorials, and join my newsletter here : https://eranfeit.net/blog

#LipSync #SadTalker

Enjoy

Eran