Installation Guide

Get Deep-Live-Cam up and running on your system

System Requirements

  • Python: 3.10 (required for macOS, recommended for others)
  • Operating System: Windows, macOS, or Linux
  • RAM: 4GB minimum (8GB+ recommended)
  • Storage: ~500MB for installation, ~300MB for models
  • GPU: Optional but recommended for better performance

Step 1: Clone the Repository

Start by cloning the Deep-Live-Cam repository from GitHub:

git clone https://github.com/hacksider/Deep-Live-Cam.git
cd Deep-Live-Cam

Step 2: Set Up Python Environment

Create a virtual environment to isolate dependencies:

python -m venv venv

Activate the virtual environment:

# Windows
venv\Scripts\activate

# macOS/Linux
source venv/bin/activate

Step 3: Install Dependencies

Install the required dependencies:

pip install -r requirements.txt

For GFPGAN and BasicSR compatibility:

pip install git+https://github.com/xinntao/BasicSR.git@master
pip uninstall gfpgan -y
pip install git+https://github.com/TencentARC/GFPGAN.git@master

Step 4: Run Deep-Live-Cam

For CPU-only execution:

python run.py

Note: Initial execution will download models (~300MB).

GPU Acceleration Setup

For better performance, set up GPU acceleration based on your hardware:

CUDA (NVIDIA GPUs)

  1. Install CUDA Toolkit 12.8.0
  2. Install cuDNN v8.9.7 for CUDA 12.x
  3. Install PyTorch with CUDA support:
    pip install -U torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
  4. Install ONNX Runtime GPU:
    pip uninstall onnxruntime onnxruntime-gpu
    pip install onnxruntime-gpu==1.21.0
  5. Run with CUDA:
    python run.py --execution-provider cuda

CoreML (Apple Silicon - M1/M2/M3)

  1. Ensure you're using Python 3.10
  2. Install ONNX Runtime Silicon:
    pip uninstall onnxruntime onnxruntime-silicon
    pip install onnxruntime-silicon==1.13.1
  3. Run with CoreML (use python3.10 explicitly):
    python3.10 run.py --execution-provider coreml

Important: You must use Python 3.10, not newer versions like 3.11 or 3.13.

DirectML (Windows)

  1. Install ONNX Runtime DirectML:
    pip uninstall onnxruntime onnxruntime-directml
    pip install onnxruntime-directml==1.21.0
  2. Run with DirectML:
    python run.py --execution-provider directml

OpenVINO (Intel)

  1. Install ONNX Runtime OpenVINO:
    pip uninstall onnxruntime onnxruntime-openvino
    pip install onnxruntime-openvino==1.21.0
  2. Run with OpenVINO:
    python run.py --execution-provider openvino

Troubleshooting

macOS Issues

  • If you get a _tkinter error, reinstall tkinter: brew reinstall python-tk@3.10
  • Always use python3.10 explicitly if you have multiple Python versions
  • Check that models are in the correct folder if you encounter model loading errors

General Issues

  • Ensure all dependencies are installed correctly
  • Check that your Python version is compatible (3.10 recommended)
  • Verify that your GPU drivers are up to date (for GPU acceleration)
  • Check the FAQ for common problems

Next Steps

Once installed, you can: