Hugging Face Diffusion Models Course

Overview

In this free course, you will:

👩‍🎓 Study the theory behind diffusion models
🧨 Learn how to generate images and audio with the popular 🤗 Diffusers library
🏋️‍♂️ Train your own diffusion models from scratch
📻 Fine-tune existing diffusion models on new datasets
🗺 Explore conditional generation and guidance
🧑‍🔬 Create your own custom diffusion model pipelines

Prerequisites

This course requires a good level in Python and a grounding in deep learning and Pytorch. If it’s not the case yet, you can check these free resources:

Python: https://www.udacity.com/course/introduction-to-python—ud1110
Intro to Deep Learning with PyTorch: https://www.udacity.com/course/deep-learning-pytorch—ud188
PyTorch in 60min: https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html

To upload your models to the Hugging Face Hub, you’ll need an account. You can create one for free at the following address: https://huggingface.co/join.

What is the syllabus?

The course consists in four units. Each unit is made up of a theory section, which also lists resources/papers, and two notebooks. More specifically, we have:

Unit 1: Introduction to diffusion models
Introduction to 🤗 Diffusers and implementation from 0
Unit 2: Finetuning and guidance
Finetuning a diffusion model on new data and adding guidance.
Unit 3: Stable Diffusion
Exploring a powerful text-conditioned latent diffusion model
Unit 4: Doing more with diffusion
Advanced techniques for going further with diffusion