Requirements

You can run Avatarify in two modes: locally and remotely.

To run Avatarify locally you need a CUDA-enabled (NVIDIA) video card. Otherwise it will fallback to the central processor and run very slowly. These are performance metrics for some hardware:

  • GeForce GTX 1080 Ti: 33 frames per second
  • GeForce GTX 1070: 15 frames per second
  • GeForce GTX 950: 9 frames per second

This guide is tested for Windows 10.

  1. Install Miniconda Python 3.8.
  2. Install Git.
  3. Press Windows button and type "miniconda". Run suggested Anaconda Prompt.
  4. Download and install Avatarify (please copy-paste these commands and don't change them):
git clone https://github.com/alievk/avatarify-python.git
cd avatarify-python
scripts\install_windows.bat
  1. Download network weights and place vox-adv-cpk.pth.tar file in the avatarify-python directory (don't unpack it).
  2. Run run_windows.bat. If installation was successful, two windows "cam" and "avatarify" will appear. Leave these windows open for the next installation steps.
  3. Install OBS Studio for capturing Avatarify output.
  4. Install VirtualCam plugin. Choose Install and register only 1 virtual camera.
  5. Run OBS Studio.
  6. In the Sources section, press on Add button ("+" sign), select Windows Capture and press OK. In the appeared window, choose "[python.exe]: avatarify" in Window drop-down menu and press OK. Then select Edit -> Transform -> Fit to screen.
  7. In OBS Studio, go to Tools -> VirtualCam. Check AutoStart, set Buffered Frames to 0 and press Start.
  8. Now OBS-Camera camera should be available in Zoom (or other videoconferencing software).


The steps 10-11 are required only once during setup.