Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/hacksider/Deep-Live-Cam/llms.txt

Use this file to discover all available pages before exploring further.

Deep-Live-Cam requires a specific set of tools before you can install its Python dependencies. Python 3.11 is the only supported version — the project does not work with Python 3.12 or 3.13 due to incompatibilities in some dependencies. Follow the steps below to set up your environment on Windows, macOS, or Linux.
Python 3.11 is required. Do not use Python 3.12 or 3.13. On macOS, always use the python3.11 command explicitly if you have multiple Python versions installed to avoid loading the wrong interpreter.

​
Prerequisites

Before cloning the repository, make sure the following tools are installed on your system:
  • Python 3.11 — the only supported version
  • pip — bundled with Python; used to install Python packages
  • git — needed to clone the repository
  • ffmpeg — required for video processing; the application will not start without it
  • Visual Studio 2022 Runtimes (Windows only) — required C++ runtime libraries

​
Install ffmpeg

Run the following command in PowerShell to install ffmpeg automatically:
iex (irm ffmpeg.tc.ht)

​
Install Visual Studio 2022 Runtimes (Windows only)

Download and install the Visual C++ Build Tools from Microsoft. These runtimes are required by several compiled Python packages that Deep-Live-Cam depends on.

​
Installation

1

Clone the repository

Clone the Deep-Live-Cam repository from GitHub:
git clone https://github.com/hacksider/Deep-Live-Cam.git
cd Deep-Live-Cam
2

Install Python 3.11 (macOS only)

On macOS, use Homebrew to install the correct Python version and its tkinter package (required for the GUI):
brew install python@3.11
brew install python-tk@3.11
If you get an error about _tkinter missing when launching the app, reinstall the package with brew reinstall python-tk@3.11.
3

Create a virtual environment

Using a virtual environment isolates Deep-Live-Cam’s dependencies from your system Python installation and avoids version conflicts.
python -m venv venv
venv\Scripts\activate
4

Install Python dependencies

With the virtual environment active, install all required packages:
pip install -r requirements.txt
This installs packages including insightface, onnxruntime, opencv-python, PySide6, numpy, and others listed in requirements.txt.
5

Download the AI models

See Download and configure AI models for instructions on downloading the required ONNX model files and placing them in the models/ folder.
6

Run Deep-Live-Cam

Start the application with:
python run.py
The first time you run the application, InsightFace will automatically download the buffalo_l face analysis model (~300 MB). This only happens once; subsequent launches use the cached files.

​
Reinstalling the virtual environment

If something goes wrong with your environment, remove it and start fresh: 
deactivate
rm -rf venv
python -m venv venv
source venv/bin/activate   # or venv\Scripts\activate on Windows
pip install -r requirements.txt
If you encounter errors related to gfpgan or basicsr on macOS, reinstall them from source: 
pip install git+https://github.com/xinntao/BasicSR.git@master
pip uninstall gfpgan -y
pip install git+https://github.com/TencentARC/GFPGAN.git@master

Build docs developers (and LLMs) love

Get started for freeTalk to us