Advanced Diffusion Model Architectures and Training
Chapter 1: Foundation Review and Advanced Noise Schedules
Recap: Denoising Diffusion Probabilistic Models (DDPM)
Recap: Denoising Diffusion Implicit Models (DDIM)
Mathematical Underpinnings: Score Matching and ODEs
Limitations of Standard Noise Schedules
Designing Custom Noise Schedules
Learned Variance Schedules
Hands-on Practical: Implementing Noise Schedule Variants
Chapter 2: Advanced U-Net Architectures
The Standard U-Net in Diffusion Models
Attention Mechanisms in U-Nets (Self-Attention, Cross-Attention)
Integrating Time Embeddings in U-Nets
Advanced Conditioning Input Integration
Architectural Variants for Efficiency (Depth, Width, Pooling)
Normalization Techniques (GroupNorm, AdaLN)
Hands-on Practical: Modifying a U-Net with Attention
Chapter 3: Transformer-Based Diffusion Models
Motivation for Transformers in Generative Modeling
Adapting Transformers for Image Data (ViT, Patch Embeddings)
Diffusion Transformers (DiT): Architecture Overview
Conditioning in Diffusion Transformers
Comparison: U-Nets vs. Transformers for Diffusion
Implementation Considerations for DiTs
Hands-on Practical: Building a Simple DiT Block
Chapter 4: Advanced Training Techniques
Classifier Guidance: Principles and Implementation
Classifier-Free Guidance (CFG): Theory and Benefits
Implementing and Tuning CFG Scale
Advanced Loss Function Formulations (v-prediction, L_simple)
Model Parameterization (epsilon-prediction vs. x0-prediction)
Techniques for Training Stability (Gradient Clipping, EMA)
Mixed-Precision Training for Diffusion Models
Hands-on Practical: Implementing Classifier-Free Guidance
Chapter 5: Consistency Models
Motivation: The Need for Faster Sampling
Core Idea: Consistency Property
Consistency Model Training: Distillation Approach
Consistency Model Training: Standalone Approach
Sampling from Consistency Models (Single-step and Multi-step)
Architecture Considerations for Consistency Models
Trade-offs: Speed vs. Quality
Hands-on Practical: Basic Consistency Distillation
Chapter 6: Advanced Sampling and Optimization
Higher-Order Solvers (DPM-Solver, UniPC)
Stochastic Sampling Variants
Guided Sampling Refinements
Troubleshooting Sampling Issues (Artifacts, Blurriness)
Model Distillation for Diffusion
Quantization of Diffusion Models
Hardware Acceleration Considerations (GPU Kernels, Compilation)
Hands-on Practical: Comparing Advanced Samplers
Model Parameterization (epsilon-prediction vs. x0-prediction)
Was this section helpful?
- Denoising Diffusion Probabilistic Models, Jonathan Ho, Ajay Jain, Pieter Abbeel, 2020 Advances in Neural Information Processing Systems (NeurIPS) DOI: 10.48550/arXiv.2006.11239 - Introduces the Denoising Diffusion Probabilistic Models framework and establishes the standard $\epsilon$-prediction objective.
- Generative Modeling by Estimating Gradients of the Data Distribution, Yang Song, Stefano Ermon, 2019 Advances in Neural Information Processing Systems (NeurIPS) DOI: 10.48550/arXiv.1907.05600 - Establishes the connection between denoising score matching and likelihood-based generative models, foundational for understanding $\epsilon$-prediction's theoretical link.
- Elucidating the Design Space of Diffusion-Based Generative Models, Tero Karras, Miika Aittala, Timo Aila, Samuli Laine, 2022 Advances in Neural Information Processing Systems (NeurIPS) DOI: 10.48550/arXiv.2206.00364 - Provides a unified framework for diffusion models, comparing different parameterizations ($\epsilon$, $x_0$, $v$) and their impact on training stability and sample quality.