This is a complete, pre-packaged Conda environment for the Deep-Live-Cam face-swapping tool.
It saves you from manually installing CUDA, PyTorch, or hunting for DLL files.
1# Create the environments folder if it doesn't exist
2mkdir %USERPROFILE%\miniconda3\envs\deeplivecam
3
4# Extract the package (Update the path to where you downloaded the file)
5tar -xzf C:\path\to\deeplivecam.tar.gz -C %USERPROFILE%\miniconda3\envs\deeplivecam
6
7# Activate the environment
8conda activate deeplivecam
9
10# Navigate to the app folder
11cd Desktop\Deep-Live-Cam
12
13# Run the GPU command
14python run.py --execution-provider cuda --max-memory 5 --frame-processor face_swapper
15
16
17## `--max-memory` Flag Explained
18
19This flag prevents GPU crashes by limiting VRAM usage:
20
21- `--max-memory 5` = Use max 5 GB (leaves 1 GB free for system)
22- For 6 GB GPUs (RTX 4050/3060): Use `--max-memory 5`
23- For 8 GB GPUs (RTX 4060/4070): Use `--max-memory 7`
24- For 12 GB+ GPUs: Can omit or use `--max-memory 10`
25
26**Why?** Without this limit, the program may try to use all available VRAM, causing Windows to crash the application.
