nagadit/DeepFaceLab_Linux

DeepFaceLab is the leading software for creating deepfakes.

Using

1. Install Anaconda

Anaconda is the preferred method of installing DeepFaceLab on Linux. Just follow the tutorial.

2. Install System Dependencies

You will need FFMpeg, Git, and the most recent NVIDIA driver for your system to use this project.

If you are here, then you already have everything...

3. Install DeepFaceLab

Just run it in the terminal.

Check latest cudnn and cudatoolkit version for your GPU device.

 conda create -n deepfacelab -c main python=3.7 cudnn=7.6.5 cudatoolkit=10.1.243
 conda activate deepfacelab
 git clone --depth 1 https://github.com/nagadit/DeepFaceLab_Linux.git
 cd DeepFaceLab_Linux
 git clone --depth 1 https://github.com/iperov/DeepFaceLab.git
 python -m pip install -r ./DeepFaceLab/requirements-cuda.txt

you can confirm your gpu is working correctly by running the following code and seeing what messages pop up:

python -c "import tensorflow as tf;print(tf.__version__)"

If the scripts can't seem to access the GPU and you're having issues with cuda version mismatches when running nvidia-smi, they can sometimes be remedied by simply running

conda install tensorflow-gpu==2.4.1

4. Download Pretrain (optional)

Use script 4.1 from the scripts directory.

Or download manually

CelebA

FFHQ

Quick96

5. Navigate to the scripts directory and begin using DeepFaceLab_Linux ᗡ:

Run all scripts with BASH shell

bash 1_clear_workspace.sh

etc