Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Getting the latest versions of Disco Diffusion to work locally, instead of colab. Including how I run this on Windows, despite some Linux only dependencies ;)
| Date | Stars |
|---|---|
| 2026-07-24 | 316 |
| 2026-07-25 | 316 |
| 2026-07-28 | 316 |
| 2026-07-30 | 316 |
| 2026-08-06 | 316 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Disco Diffusion v5 Turbo, with 3D animation, running locally.
Getting the latest versions of Disco Diffusion ([at time of writing this is v5 with Turbo and 3D Animation](https://colab.research.google.com/github/zippy731/disco-diffusion-turbo/blob/main/Disco_Diffusion_v5_Turbo_%5Bw_3D_animation%5D.ipynb)) to work locally, instead of colab. Including how I run this on Windows, despite some Linux only dependencies ;). Now includes an experimental batch mode to create as many videos as you want with different prompts, with only 1 run.
If you run into any issues, feel free to open an issue and I’ll do my best to help troubleshoot. Be as specific as possible. For example, if you get an error message at any point you need to include this in the issue, alongside operating system and computer specs.
## Examples
<img src="./examples/self_portrait_of_an_AI.png" width="512px"></img>
<img src="./examples/terrarium.jpg" width="256px"></img><img src="./examples/abandoned_shopping_mall.jpeg" width="256px"></img>
<img src="./examples/retro_playroom.jpg" width="256px"></img><img src="./examples/purity_and_grace.png" width="256px"></img>
## How to run this on Windows
The same steps should work on Linux, starting from step 3.
Requirements:
* Nvidia GPU with at least 8GB VRAM. >12GB is recommended.
* Windows 10 or 11
### Step 1: Update windows
Windows 11: Windows 11 should work but it doesn't hurt to update to the latest version before continuing :) (note though that I've created and tested this on Windows 10)
Windows 10: You must be running at least feature update 21H2 for your GPU to work. To check which version you're running, open cmd and type:
winver
If you’re on 21H2 or later, you’re good to go. If not, try updating Windows by typing “check for updates” in the start menu and using the built in tool. For me personally, the required update was not showing, but I was able to install it by using the [Windows 10 Update Assistant](https://support.microsoft.com/en-us/topic/windows-10-update-assistant-3550dfb2-a015-7765-12ea-fba2ac36fb3f).
### Step 2: install WSL2
The way we’ll use Linux only dependencies is by installing the latest version of the Windows Subsystem for Linux (WSL2). This will run a virtual machine–like Ubuntu installation on Windows. However, Microsoft have implemented this at a very low level, meaning almost no performance hit and GPU support!
For the latest instructions on this, follow the [official Microsoft guide](https://docs.microsoft.com/en-us/windows/wsl/install).
Briefly, just open a Windows Powershell as administrator, and type:
wsl —-install
It might request a restart, and when you restart your computer you’ll have an app in the start menu or task bar called “Ubuntu”!
### Step 3: install Anaconda on Ubuntu
We’ll need to install Anaconda inside our Ubuntu environment to manage packages easily. Open your new Ubuntu app (and fix any errors that come up on first launch. I had a few, but they were either self explanatory or fixed easily with some quick Googling).
Now you want to download, then run, the Linux Anaconda installer as follows. If you’re following this much later than March 2022 you can replace the url below with the latest version from [the Anaconda website](https://www.anaconda.com/products/individual?modal=nucleus).
mkdir Downloads
cd Downloads
wget https://repo.anaconda.com/archive/Anaconda3-2021.11-Linux-x86_64.sh
bash Anaconda3-2021.11-Linux-x86_64.sh
Follow the on-screen instructions. Ie type yes when it asks you to, and ask it to run conda init for you when prompted.
Close your Ubuntu terminal and open it again.
Now type and run
conda —-help
If it gives you a long list of conda options, that means it’s successfully installed Anaconda within Ubuntu!
### Step 4: creating our environment
We’ll now create and activate a conda environment (inside Ubuntu) with all the appropriate dependencies.
conda create -n pytorch_110
conda activate pytorch_Excerpt of 9,844 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:afdfe2dbea9b7e2d, topic:text-to-image
matched fp:afdfe2dbea9b7e2d, topic:clip