The Annotated Diffusion Model

What changed

We'll go over the original DDPM paper by (Ho et al., 2020), implementing it step-by-step in PyTorch, based on Phil Wang's implementation - which itself is based on the original TensorFlow implementation. Note that the idea of diffusion for generative modeling was actually already introduced in (Sohl-Dickstein et al., 2015). However, it took until (Song et al., 2019) (at Stanford University), and then (Ho et al., 2020) (at Google Brain) who independently improved the approach.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• Introducing Würstchen: Fast Diffusion for Image Generation
• Using LoRA for Efficient Stable Diffusion Fine-Tuning
• Accelerating Stable Diffusion Inference on Intel CPUs

• Introducing Würstchen: Fast Diffusion for Image Generation similarity 0.24
• Using LoRA for Efficient Stable Diffusion Fine-Tuning similarity 0.23
• Accelerating Stable Diffusion Inference on Intel CPUs similarity 0.22