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
Conditioning in Diffusion Transformers
Was this section helpful?
- Scalable Diffusion Models with Transformers, William Peebles, Saining Xie, 2023 Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (IEEE) DOI: 10.1109/ICCV51070.2023.01168 - Introduces Diffusion Transformers (DiTs) and the AdaLN-Zero conditioning mechanism, which is central to the section's discussion.
- High-Resolution Image Synthesis with Latent Diffusion Models, Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer, 2022 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE) DOI: 10.1109/CVPR52688.2022.00196 - Details cross-attention for text conditioning in diffusion models, offering a comparison point for cross-attention in DiTs and U-Net architectures mentioned in the text.
- Attention Is All You Need, Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin, 2017 Advances in Neural Information Processing Systems, Vol. 30 (Curran Associates, Inc.) DOI: 10.5555/3295222.3295349 - The foundational paper introducing the Transformer architecture, which forms the basis of Diffusion Transformers.
- FiLM: Visual Reasoning with a General Conditioning Layer, Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, Aaron Courville, 2018 Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32 (Association for the Advancement of Artificial Intelligence) DOI: 10.1609/aaai.v32i1.11671 - Introduces Feature-wise Linear Modulation (FiLM), a technique that provides a broader context for adaptive normalization methods like AdaLN-Zero used in DiTs.