A playground for text-to-image enthusiasts using Stable Diffusion V2.

Also see Whisper Playground - a playground for building real-time speech2text web apps using OpenAI's Whisper

You can tinker with the DALL-E playground using a Github-hosted frontend. Follow these steps:

1. Run the DALL-E backend using Google Colab
2. Copy the URL from the output of the last executed cell. Search for the line stating with Your url is:.
3. Wait for the backend to fully load, this should take ~2min and you should see --> Image generation server is up and running!
4. Browse https://saharmor.github.io/dalle-playground/?backendUrl=https://XXXX.trycloudflare.com where the backendUrl query parameter should be the url from the previous step

General note: while it is possible to run the backend on the free tier of Google Colab, generating more than ~2 images would take >1min, which will result in a frontend timeout. Consider upgrading to Colab Pro or run the backend notebook on your stronger ML machine (e.g. AWS EC2).

Follow these steps in case you'd like to clone and run the DALL-E Playground locally:

1. Clone or fork this repository
2. Create a virtual environment cd backend && python3 -m venv ENV_NAME
3. Run virtual environment source venv/bin/activate
4. Install requirements pip install -r requirements.txt
5. Make sure you have pytorch and its dependencies installed Installation guide
6. Run web server python3 app.py --port 8080 (you can change from 8080 to your own port)
7. In a different terminal, install frontend's modules cd interface && npm install and run it npm start
8. Copy backend's url from step 5 and paste it in the backend's url input within the web app

Window's WSL2 Linux layer has some unique issues getting running with GPU support. Nvidia CUDA drivers are installed on the Windows side instead of Linux, but jax does not see the GPU without compiling from source. Here are extra instructions to get jax compiled.

1. Have a recent NVIDIA GeForce Game Ready or NVIDIA RTX Quadro driver installed in Windows
2. In Linux: Install Nvidia's CUDA toolkit, WSL instructions
3. In Linux: Install Nvidia's CuDNN library: instructions
4. In Linux: Build and install both jaxlib and jax from source, remember to enable cuda during compilation with python3 build/build.py --enable_cuda instructions
5. In compiling jaxlib, you might hit a broken configuration file, solution here: jax-ml/jax#11068
6. Follow local development instructions above

WSL2 installs are fairly bare bones, expect to install packages like npm, python3-pip and many others to get things working. More troubleshooting here

1. Make sure you have docker and The NVIDIA Container Toolkit installed

2. Clone or fork this repository

3. start server docker-compose up, add -d to docker-compose up if you'd like to run it in the background

4. The first time will take some time to download the images, models and other dependencies. models and other dependencies are downloaded only once, and then cached.

5. Copy backend's url from step 2 and paste it in the backend's url input within the web app.

   webapp at http://localhost:3000/dalle-playground

The original reposistory used @borisdayma's DALL-E Mini.