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
Motivation for Conditional Generation
Was this section helpful?
- Denoising Diffusion Probabilistic Models, Jonathan Ho, Ajay Jain, and Pieter Abbeel, 2020 Advances in Neural Information Processing Systems (NeurIPS) DOI: 10.48550/arXiv.2006.11239 - This foundational paper introduced the Denoising Diffusion Probabilistic Model (DDPM), establishing the core framework for unconditional image generation that subsequent conditional methods build upon.
- Diffusion Models Beat GANs on Image Synthesis, Prafulla Dhariwal and Alex Nichol, 2021 Advances in Neural Information Processing Systems (NeurIPS) DOI: 10.48550/arXiv.2105.05233 - This work significantly advanced diffusion models, demonstrating their superior image generation quality and introducing classifier guidance, an early and effective method for conditional generation.
- Classifier-Free Diffusion Guidance, Jonathan Ho and Tim Salimans, 2022 arXiv preprint arXiv:2207.12598 DOI: 10.48550/arXiv.2207.12598 - Introduces classifier-free guidance, a widely adopted technique that enables effective conditional generation without needing an external classifier, streamlining the process for many applications.
- High-Resolution Image Synthesis with Latent Diffusion Models, Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer, 2022 CVPR 2022 DOI: 10.48550/arXiv.2112.10752 - Presents Latent Diffusion Models (LDMs), which enable efficient high-resolution image generation and are a foundational architecture for popular text-to-image models like Stable Diffusion, showcasing practical conditional generation.