Installing faceswap

Prerequisites

Machine learning essentially involves a ton of trial and error. You’re letting a program try millions of different settings to land on an algorithm that sort of does what you want it to do. This process is really really slow unless you have the hardware required to speed this up.

The type of computations that the process does are well suited for graphics cards, rather than regular processors. It is pretty much required that you run the training process on a desktop or server capable GPU. Running this on your CPU means it can take weeks to train your model, compared to several hours on a GPU.

Hardware Requirements

TL;DR: you need at least one of the following:

Supported operating systems

Alternatively, there is a docker image that is based on Debian.

Important before you proceed

In its current iteration, the project relies heavily on the use of the command line, although a gui is available. if you are unfamiliar with command line tools, you may have difficulty setting up the environment and should perhaps not attempt any of the steps described in this guide. This guide assumes you have intermediate knowledge of the command line.

The developers are also not responsible for any damage you might cause to your own computer.

Linux, Windows and macOS Install Guide

Installer

Windows, Linux and macOS all have installers which set up everything for you. You can download the installer from https://github.com/deepfakes/faceswap/releases.

If you have issues with the installer then read on for the more manual way to install faceswap on Windows.

Manual Install

Setting up faceswap can seem a little intimidating to new users, but it isn’t that complicated, although a little time consuming. It is recommended to use Linux where possible as Windows will hog about 20% of your GPU Memory, making faceswap run a little slower, however using Windows is perfectly fine and 100% supported.

Prerequisites

Anaconda

Download and install the latest Python 3 Anaconda from: https://www.anaconda.com/download/. Unless you know what you are doing, you can leave all the options at default.

Git

Download and install Git for Windows: https://git-scm.com/download/win. Unless you know what you are doing, you can leave all the options at default.

Setup

Reboot your PC, so that everything you have just installed gets registered.

Anaconda

Set up a virtual environment

Entering your virtual environment

To enter the virtual environment:

faceswap

Easy install

Manual install

Do not follow these steps if the Easy Install above completed succesfully. If you are using an Nvidia card make sure you have the correct versions of Cuda/cuDNN installed for the required version of Tensorflow

Running faceswap

Create a desktop shortcut

A desktop shortcut can be added to easily launch straight into the faceswap GUI:

Updating faceswap

It’s good to keep faceswap up to date as new features are added and bugs are fixed. To do so:

macOS (Apple Silicon) Install Guide

macOS now has an installer which sets everything up for you, but if you run into difficulties and need to set things up manually, the steps are as follows:

Prerequisites

OS

macOS 12.0+

XCode Tools

xcode-select --install

XQuartz

Download and install from:

Conda

Download and install the latest Conda env from:

Install Conda:

$ chmod +x ~/Downloads/Miniforge3-MacOSX-arm64.sh
$ sh ~/Downloads/Miniforge3-MacOSX-arm64.sh
$ source ~/miniforge3/bin/activate

Setup

Create and Activate the Environment

$ conda create --name faceswap python=3.10
$ conda activate faceswap

faceswap

Easy install

$ python setup.py

General Install Guide

Installing dependencies

Git

Git is required for obtaining the code and keeping your codebase up to date. Obtain git for your distribution from the git website.

Python

The recommended install method is to use a Conda3 Environment as this will handle the installation of Nvidia’s CUDA and cuDNN straight into your Conda Environment. This is by far the easiest and most reliable way to setup the project.

Alternatively you can install Python (3.10 64-bit) for your distribution (links below.) If you go down this route and are using an Nvidia GPU you should install CUDA (https://developer.nvidia.com/cuda-zone) and cuDNN (https://developer.nvidia.com/cudnn). for your system. If you do not plan to build Tensorflow yourself, make sure you install the correct Cuda and cuDNN package for the currently installed version of Tensorflow (Current release: Tensorflow 2.9. Release v1.0: Tensorflow 1.15). You can check for the compatible versions here: (https://www.tensorflow.org/install/source#gpu).

Virtual Environment

It is highly recommended that you setup faceswap inside a virtual environment. In fact we will not generally support installations that are not within a virtual environment as troubleshooting package conflicts can be next to impossible.

If using Conda3 then setting up virtual environments is relatively straight forward. More information can be found at Conda Docs

If using a default Python distribution then virtualenv and virtualenvwrapper may help when you are not using docker.

Getting the faceswap code

It is recommended to clone the repo with git instead of downloading the code from http://github.com/deepfakes/faceswap and extracting it as this will make it far easier to get the latest code (which can be done from the GUI). To clone a repo you can either use the Git GUI for your distribution or open up a command prompt, enter the folder where you want to store faceswap and enter:

git clone https://github.com/deepfakes/faceswap.git

Setup

Enter your virtual environment and then enter the folder that faceswap has been downloaded to and run:

python setup.py

If setup fails for any reason you can still manually install the packages listed within the files in the requirements folder.

About some of the options

Docker Install Guide

This Faceswap repo contains Docker build scripts for CPU and Nvidia backends. The scripts will set up a Docker container for you and install the latest version of the Faceswap software.

You must first ensure that Docker is installed and running on your system. Follow the guide for downloading and installing Docker from their website:

Once Docker is installed and running, follow the relevant steps for your chosen backend

Docker CPU

To run the CPU version of Faceswap follow these steps:

  1. Build the Docker image For faceswap: 
    docker build \
-t faceswap-cpu \
https://raw.githubusercontent.com/deepfakes/faceswap/master/Dockerfile.cpu

  2. Launch and enter the Faceswap container:

    a. For the headless/command line version of Faceswap run:

     docker run --rm -it faceswap-cpu

    You can then execute faceswap the standard way:

     python faceswap.py --help

    b. For the GUI version of Faceswap run:

     xhost +local: && \
 docker run --rm -it \
 -v /tmp/.X11-unix:/tmp/.X11-unix \
 -e DISPLAY=${DISPLAY} \
 faceswap-cpu

    You can then launch the GUI with

     python faceswap.py gui

    ## Docker Nvidia To build the NVIDIA GPU version of Faceswap, follow these steps:

  3. Nvidia Docker builds need extra resources to provide the Docker container with access to your GPU.

    a. Follow the instructions to install and apply the Nvidia Container Toolkit for your distribution from:

    • https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html

    b. If Docker is already running, restart it to pick up the changes made by the Nvidia Container Toolkit.

  4. Build the Docker image For faceswap 
    docker build \
-t faceswap-gpu \
https://raw.githubusercontent.com/deepfakes/faceswap/master/Dockerfile.gpu

  5. Launch and enter the Faceswap container:

    a. For the headless/command line version of Faceswap run:

     docker run --runtime=nvidia --rm -it faceswap-gpu

    You can then execute faceswap the standard way:

     python faceswap.py --help

    b. For the GUI version of Faceswap run:

     xhost +local: && \
 docker run --runtime=nvidia --rm -it \
 -v /tmp/.X11-unix:/tmp/.X11-unix \
 -e DISPLAY=${DISPLAY} \
 faceswap-gpu

    You can then launch the GUI with

     python faceswap.py gui

    Run the project

    Once all these requirements are installed, you can attempt to run the faceswap tools. Use the -h or --help options for a list of options.

python faceswap.py -h

or run with gui to launch the GUI

python faceswap.py gui

Proceed to ../blob/master/USAGE.md

Notes

This guide is far from complete. Functionality may change over time, and new dependencies are added and removed as time goes on.

If you are experiencing issues, please raise them in the faceswap Forum instead of the main repo. Usage questions raised in the issues within this repo are liable to be closed without response.