Info-icon.png We have moved to https://openmodeldb.info/. This new site has a tag and search system, which will make finding the right models for you much easier! If you have any questions, ask here: https://discord.gg/cpAUpDK

Installing ESRGAN and/or BasicSR on Arch Linux

From Upscale Wiki
This is the approved revision of this page, as well as being the most recent.
Jump to navigation Jump to search

For this guide you will need either Arch Linux or another Linux Distribution that is based on it.

Guide Dependencies

If you don't have them installed already, you will need base-devel, git and yay to follow the steps of this guide: Open the terminal and enter:

sudo pacman -S base-devel git && git clone https://aur.archlinux.org/yay.git && cd yay && makepkg -si && cd .. && rm -rf yay

ESRGAN / BasicSR dependencies

  • If you have and use an NVIDIA GPU, enter the following into the terminal:
    sudo pacman -Syu python-pip python-pytorch-opt-cuda
    • In addition, you'll also need to install these dependencies directly from Pytorch's website:
      sudo pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
  • If you don't have an NVIDIA GPU (AMD or Intel), enter the following into the terminal:
    sudo pacman -Syu python-pip python-pytorch
  • Once those dependencies are installed, enter the following commands into the terminal to install the rest of the required dependencies:
    sudo pip install -r /path/to/BasicSR/requirements.txt --force-reinstall -U
    sudo pip install basicsr

Cloing / Installing ESRGAN

To clone ESRGAN (old architecture / BlueAmulet Fork) Go into the folder where you want to put the ESRGAN folder/installation in, then clone it by entering the following into the terminal: git clone https://github.com/JoeyBallentine/ESRGAN.git

Cloning / Installing traiNNer

To clone traiNNer (Victorc's fork) Go into the folder where you want to put the traiNNer folder/installation in, then clone it by entering the following into the terminal:
git clone https://github.com/victorca25/traiNNer