Having established how diffusion models are trained to predict noise within corrupted data, this chapter focuses on the inverse operation: generating novel data samples. We will examine how to start with pure noise, typically sampled from a Gaussian distribution xT∼N(0,I), and iteratively apply the learned reverse diffusion process to produce a clean data point x0.
You will learn the step-by-step procedure for the standard Denoising Diffusion Probabilistic Models (DDPM) sampling algorithm. We will then introduce Denoising Diffusion Implicit Models (DDIM), a related but often faster sampling technique that offers different trade-offs between speed and sample quality. Finally, we will cover the practical implementation details required to build these sampling loops in code.
5.1 Generating Data from Noise
5.2 The DDPM Sampling Algorithm
5.3 Understanding Sampling Variance
5.4 Introduction to Faster Sampling: DDIM
5.5 The DDIM Sampling Algorithm
5.6 Trade-offs Between DDPM and DDIM
5.7 Practice: Implementing Sampling Loops
© 2025 ApX Machine Learning