Skip to content

Instantly share code, notes, and snippets.

@spiral6
Last active July 26, 2022 18:10
Show Gist options
  • Save spiral6/31ac34f3fb1d8ce33022e2178380a4ac to your computer and use it in GitHub Desktop.
Save spiral6/31ac34f3fb1d8ce33022e2178380a4ac to your computer and use it in GitHub Desktop.
Installation Guide for AI Dungeon 2 (Windows)

Installation Guide for AI Dungeon 2 (Windows) (updated 12/13/19)

1. Run PowerShell as Administrator as pictured below.

image

2. Install Chocolatey

Go to your PowerShell window and copy and paste the following command in.
If you have any questions or qualms about doing so, see the official Chocolatey page here.

Set-ExecutionPolicy Bypass -Scope Process -Force; iex ((New-Object System.Net.WebClient).DownloadString('https://chocolatey.org/install.ps1'))

image

3. Install dependencies (Python 3.8 apparently does not work)

Type in the following commands in your PowerShell window.
choco install python --version 3.7.4
choco install git

Go ahead and type in the following command to make sure your Python package manager pip is up to date as well.
python -m pip install --upgrade pip

Note of advice: if you are attempting to run this on Windows Subsystem for Linux (WSL), replace any commands with python with the term python3 instead.

4. Navigate to the folder you wish to save AI Dungeon in, and clone repo.

Type in the following commands in your PowerShell window.
cd C:\Users\<username>\AIDungeon2
(create the folder if it doesn't exist)
git clone https://github.com/AIDungeon/AIDungeon/
(Ensure that requirements.txt is in the root of the folder.)

5. Download the model via torrent

Type in the following command in your PowerShell window.
choco install qbittorrent
Open qbittorrent. Click the magnet icon in the top left.
image
Copy the magnet link here.

magnet:?xt=urn:btih:b343b83b35bff774dab13e0281ce13b3daf37d3e&dn=model_v5&tr=udp%3a%2f%2ftracker.coppersurfer.tk%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.leechers-paradise.org%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.opentrackr.org%3a1337%2fannounce&tr=udp%3a%2f%2ftracker.pomf.se%3a80%2fannounce&tr=udp%3a%2f%2ftracker.openbittorrent.com%3a80%2fannounce&tr=udp%3a%2f%2fp4p.arenabg.com%3a1337%2fannounce&tr=udp%3a%2f%2f9.rarbg.me%3a2710%2fannounce&tr=udp%3a%2f%2f9.rarbg.to%3a2710%2fannounce&tr=udp%3a%2f%2fexodus.desync.com%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.tiny-vps.com%3a6969%2fannounce&tr=udp%3a%2f%2fopen.stealth.si%3a80%2fannounce&tr=udp%3a%2f%2fdenis.stalker.upeer.me%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.torrent.eu.org%3a451%2fannounce&tr=udp%3a%2f%2ftracker.moeking.me%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.cyberia.is%3a6969%2fannounce&tr=udp%3a%2f%2fopen.demonii.si%3a1337%2fannounce&tr=udp%3a%2f%2fipv4.tracker.harry.lu%3a80%2fannounce&tr=udp%3a%2f%2ftracker3.itzmx.com%3a6961%2fannounce&tr=udp%3a%2f%2fzephir.monocul.us%3a6969%2fannounce&tr=udp%3a%2f%2fxxxtor.com%3a2710%2fannounce

Add the magnet link to the box as pictured below.
image
Save the model file accordingly, as pictured below.
image

6. Install NVIDIA CUDA Toolkit

Install the latest CUDA from NVIDIA's site.
At the time of the writing of this guide, I had installed CUDA Toolkit 10.2. It was fully functional with AI Dungeon 2.

7. Install Python dependencies

Go back to your PowerShell admin window.
The current working directory of the window should be in C:\Users\<username>\AIDungeon2\AIDungeon or wherever the .git folder is located. Type in:
python -m pip install -r requirements.txt

8. Play

Finally, go ahead and type in:
python .\play.py

9. Optional GPU support (only use if your NVIDIA GPU has 12 GB of VRAM)

Open the link to the missing CuDNN .dll files here. (archive.org)
Follow the instructions here to find out where to place the files.

If you have any questions, comments or updates to this guide, please feel free to submit a pull request or comment below. Thanks.

@straypup
Copy link

its unclear how to get AIdungeon to recognize that i have the CuDNN files in the proper place

@ServOKio
Copy link

its unclear how to get AIdungeon to recognize that i have the CuDNN files in the proper place

same question

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment