Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget This repository provides a minimalistic implementation of our approach to training large-scale diffusion models from scratch on an extremely low budget. In particular, using only 37M publicly available real and synthetic images, we train a 1.16 billion parameter sparse transformer with a total cost of only $1,890 and achieve an FID of 12.7 in zero-shot generation on the COCO dataset. Please find further details in the offi...