text-to-image stable-diffusion architecture

The "brutal-arch" Dreambooth model was trained by Gia Dalakas with TheLastBen's fast-DreamBooth notebook.

Test the concept via Google Colab (https://colab.research.google.com/drive/1sONb4aAgsQv7NVbuBGsA68bwOaYOLI0z?usp=sharing)