guide to installing disco v5+ locally on windows

disco_v5_plus_Win_Install.md

Install Disco Diffusion v5 for Windows

NOTE: Pytorch3d no longer has to be compiled i have stripped out the function we use to make this a lot easier and also so we do not have to use WSL2 with linux and can now run directly on your windows system.

Comments section is not checked often for issues please join the disco diffusion discord for assistance

https://discord.gg/mK4AneuycS

You may now use the official disco diffusion notebook with this tutorial as it has been uodated to reflect the changes here for better cross platform support

This will walk you through getting your environment setup to run most of the GANs with Anaconda as a Virtual Python Environment.

System Requirements:

  OS: Windows (11/10/8/7), Ubuntu(19,20)
  GPU: Nvidia (AMD hasnt been tested)
  VRAM: 12gb+

1) Download Tools!

1. A) Cuda enabled GPU
   • Latest Nvidia Drivers
   • https://www.nvidia.com/Download/index.aspx
   • CUDA Toolkit for your version
   • https://developer.nvidia.com/cuda-downloads
   • https://docs.nvidia.com/cuda/cuda-quick-start-guide

1. B) Python (Anaconda)
   • https://www.anaconda.com/products/individual#Downloads
   • We use anaconda to make it easier to manage different projects
   • Virtual python evironment and versioning
   • Anaconda also includes Jupyter Notebook pre-installed

1. C) Git
   • https://git-scm.com/downloads
   • version control manager for code
   • we just use it to download repos from GitHub
   • Must be on system PATH, When installing select the option add to system PATH

1. D) FFmpeg
   • https://ffmpeg.org/download.html
   • Video encoding tool library
   • we use this mainly to turn image sequences into videos
   • Must be on system PATH
   • https://www.wikihow.com/Install-FFmpeg-on-Windows

1. E) ImageMagick
   • https://imagemagick.org/script/download.php
   • software suite for displaying, creating, converting, modifying, and editing raster images.
   • used in some projects but handy to have already installed

1. F) Wget
   • used to download models for projects
   • Windows users need this verison
   • https://eternallybored.org/misc/wget/
   (spoiler) Add to Path on Windows (spoiler)
   download the .exe
   create a new folder to put the .exe in (prefereable on the root of your C:/ drive)
   • e.g C:/wget/wget.exe
   open Control Panel and search for environment variables
   select the one with the shield icon Edit the system environment variables
   click the button at the bottom Environment Virables...
   under System variables find the and select the path variable
   click Edit... button and then New
   • add the new path to folder the .exe is in
   • e.g C:/wget
   once entered click Ok on each window until all 3 are closed
   for the new env variables to be used you must reopen a new Command Prompt window
   • Linux users can just use the package in their distributions

1. G) cURL
   • used to download models, some projects use this instead of wget
   • Latest versions of windows have cURL pre installed
   • Older versions that dont include cURL use this one
   • https://curl.se/windows/
   • Linux users can just use the package in their distributions

2) Install Disco Dependencies

2. A) Setup and activate conda env
   • conda create --name disco-diffusion python=3.9
   • conda activate disco-diffusion

2. B) Install a few more pip dependencies
   • pip install ipykernel opencv-python pandas regex matplotlib ipywidgets

2. C) Install Pytorch with CUDA support!
   • https://pytorch.org/get-started/locally/
   • be sure to install a version with GPU support!
   • example of what worked for me
   • conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch

2. D) Download disco diffusion repo!
   • git clone https://github.com/alembics/disco-diffusion.git
   • change directories into the downloaded repo
   • cd disco-diffusion

3) Run Disco Diffusion

there are several ways to run disco diffusion at this point:

1. [PYTHON .py]

plain python file wich means you will need to go into the file and manually find all the configuration options and change them as needed, an easy way to go about this is searching the document for #@param lines and edit ones containing that comment trailing the lines e.g. use_secondary_model = True #@param {type: 'boolean'}.

• Run disco diffusion
  • python -m disco.py

2-3. [VS .py/.ipynb]

running the .ipynb file directly in VS also requires editing of the #@param lines in the code

• Download Visual Studio
  • https://code.visualstudio.com/download
• Open the .ipynb file in VS
  • ENJOY!
  • for more interactivity see the tutorial using jupyter extension

4-5. [VS + Jupyter extension .py/.ipynb]

using the jupyter extension in VS we can get individual cell support to run the either the .ipynb or the .py file also requires editing of the #@param lines in the code

• Download Visual Studio
  • https://code.visualstudio.com/download
• Get the Jupyter Notebook extensions
  • head over the to the extensions tab in VS code
  • search for jupyter and install the one from Microsoft
  • after this is enabled the notebook should have several new toolbars and features
  • you can actually run both the .py file or .ipynb file which both support individual cells
  • ENJOY!

6. [Jupyter .ipynb]

using Jupyter notebooks to run the .ipynb file also requires editing of the #@param lines in the code

• with anaconda installed you should already have jupyter notebook installed if you dont simple run:
  pip install jupyterlab
• Run Jupyter
  • jupyter notebook
  • this launches the juptyer notebook in the current directory and open a webpage
  • under the Files tab double click and open the file named Disco-Diffusion.ipynb
  • ENJOY!

7. [Colab w/ Jupyter using colab links]

using Google Colab as a front end to get the nice view of all the editable fields while using Jupyter as middleware to connect your local resources

• with anaconda installed you should already have jupyter notebook installed if you dont simple run:
  pip install jupyterlab
• Connect to colab front end
  • pip install --upgrade jupyter_http_over_ws>=0.0.7
  • Enable the extension for jupyter
  • jupyter serverextension enable --py jupyter_http_over_ws
  • Start the jupyter server
  • jupyter notebook --NotebookApp.allow_origin='https://colab.research.google.com' --port=8888 --NotebookApp.port_retries=0 --no-browser
  • Inside google colab click the down Arrow icon next to the Connect button to view more options
  • Select connect to Local Runtime and enter the Local Host Url that was printed in the console when we started jupyter server
  • ENJOY!

Hi. Having issues with optical flow maps generation. Previously had error importing from utils.utills, got that resolved by renaming utils.utils to raftutils.utils, but now I'm getting this. Could you help please?

@pikok85 Hello. Were you able to solve the problem? I just have the same problem and don't know how to solve it.

Hello, thank you for the awesome work on this. I've managed to run all the clips without any errors but on the final diffuse I'm getting an error : TypeError: ddim_sample_loop_progressive() got an unexpected keyword argument 'transformation_fn'

Would anyone be able to shed some light? WOuld be much appreciated thank you!

Full error output :

Seed used: 1777865372
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Input In [19], in <cell line: 217>()
    216 torch.cuda.empty_cache()
    217 try:
--> 218     do_run()
    219 except KeyboardInterrupt:
    220     pass

Input In [6], in do_run()
    648     init = regen_perlin()
    650 if args.diffusion_sampling_mode == 'ddim':
--> 651     samples = sample_fn(
    652         model,
    653         (batch_size, 3, args.side_y, args.side_x),
    654         clip_denoised=clip_denoised,
    655         model_kwargs={},
    656         cond_fn=cond_fn,
    657         progress=True,
    658         skip_timesteps=skip_steps,
    659         init_image=init,
    660         randomize_class=randomize_class,
    661         eta=eta,
    662         transformation_fn=symmetry_transformation_fn,
    663         transformation_percent=args.transformation_percent
    664     )
    665 else:
    666     samples = sample_fn(
    667         model,
    668         (batch_size, 3, args.side_y, args.side_x),
   (...)
    676         order=2,
    677     )

TypeError: ddim_sample_loop_progressive() got an unexpected keyword argument 'transformation_fn'

Cell 1.3 I get this error:

ModuleNotFoundError                       Traceback (most recent call last)

Input In [4], in <cell line: 99>()
     97 from dataclasses import dataclass
     98 from functools import partial
---> 99 import cv2
    100 import pandas as pd
    101 import gc

ModuleNotFoundError: No module named 'cv2'

Anyone know how to get past this? I followed all instructions to a T. Re-did everything, still got the same error. No idea what could be wrong or different at this point.

getting same cv2 error