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
The Training Algorithm
New · Open Source
Kerb - LLM Development Toolkit
Python toolkit for building production-ready LLM applications. Modular utilities for prompts, RAG, agents, structured outputs, and multi-provider support.
Was this section helpful?
- Denoising Diffusion Probabilistic Models, Jonathan Ho, Augustin Saharia, William Chan, Chitwan Saharia, Jay Whang, Alex Ratner, Ruoxin Sang, Kevin Lin, Lihong Li, Jie Ren, Zhifeng Chen, Harrison Edwards, Andrew Brock, Prafulla Dhariwal, Alex Nichol, Heewon Kim, Fan Li, Yuval Alaluf, R. Tyler Mazaika, Sasha Sheng, Xiaoqing Ellen Tan, Adam Harley, Brian Li, Yang Song, Mohammad Norouzi, Tim Salimans, Alex Shmakov, Peter Henderson, Han Zhang, Irwan Bello, Ming-Hsuan Yang, Andrew Ng, Ian Goodfellow, Pieter Abbeel, and Durk Kingma, 2020 Advances in Neural Information Processing Systems, Vol. 33 (NeurIPS) DOI: 10.5591/978-1-57788-756-3-6840 - This foundational paper introduces the Denoising Diffusion Probabilistic Models (DDPM) and details the core training algorithm for noise prediction networks, as outlined in this section.
- Denoising Diffusion Probabilistic Models (DDPM) Conceptual Guide, Hugging Face, 2024 (Hugging Face) - This conceptual guide offers an accessible explanation of the Denoising Diffusion Probabilistic Models (DDPM) training loop, providing a clear walkthrough of the algorithm discussed in this section, aiding in practical understanding.
- High-Resolution Image Synthesis with Latent Diffusion Models, Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer, 2022 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE) DOI: 10.1109/CVPR52688.2022.01042 - This paper demonstrates the scalability and effectiveness of the core DDPM training paradigm by applying it to latent space, significantly advancing high-resolution image generation using diffusion models.
© 2025 ApX Machine LearningEngineered with