Introduction to Diffusion Models for Generative AI
Chapter 1: Generative Modeling Fundamentals
Overview of Generative Models
Motivation for Diffusion Models
The Core Idea: Noise and Denoise
Probabilistic Framework Introduction
Quiz for Chapter 1
Chapter 2: The Forward Diffusion Process
Defining the Markov Chain
Gaussian Noise Schedule
Mathematical Formulation per Step
Sampling from Intermediate Steps
Properties of the Forward Process
Practice: Simulating Forward Diffusion
Quiz for Chapter 2
Chapter 3: The Reverse Diffusion Process
The Goal: Reversing the Markov Chain
Approximating the Reverse Transition
Parameterizing the Reverse Process with Neural Networks
Predicting the Noise Component
Mathematical Formulation of the Denoising Step
Quiz for Chapter 3
Chapter 4: Model Architecture and Training
The U-Net Architecture for Noise Prediction
Integrating Timestep Information
Defining the Training Objective
Simplified Training Loss Derivation
The Training Algorithm
Hands-on Practical: Setting up the U-Net
Quiz for Chapter 4
Chapter 5: Sampling and Generation Process
Generating Data from Noise
The DDPM Sampling Algorithm
Understanding Sampling Variance
Introduction to Faster Sampling: DDIM
The DDIM Sampling Algorithm
Trade-offs Between DDPM and DDIM
Practice: Implementing Sampling Loops
Quiz for Chapter 5
Chapter 6: Conditional Generation with Diffusion Models
Motivation for Conditional Generation
Classifier Guidance
Classifier-Free Guidance (CFG)
Implementing Classifier-Free Guidance
Text Conditioning Basics
Architecture Modifications for Conditioning
Hands-on Practical: Applying Guidance
Quiz for Chapter 6
Mathematical Formulation per Step
Was this section helpful?
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics, Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan, Surya Ganguli, 2015 International Conference on Machine Learning (ICML 2015) DOI: 10.48550/arXiv.1503.03585 - This paper introduced the original Diffusion Probabilistic Models, laying the groundwork for the forward noising process through a series of Markov transitions, which is a direct precursor to DDPMs.