Get personalized book recommendations based on your reading history and preferences. Our algorithm analyzes your favorite books and reading patterns to suggest your next great read.

“Diffusion models” as a book category covers the theory and practice of probabilistic generative models that synthesize data by learning to reverse a gradual noising process. Titles in this genre typically span mathematical foundations (stochastic processes, score matching, variational inference), core algorithms like denoising diffusion probabilistic models (DDPMs) and score-based SDEs, and the architectures and training regimes that make them work (U-Nets, transformers, conditioning, classifier-free guidance). Practical works focus on building and deploying systems for images, audio, and video—especially text-to-image via latent diffusion—covering datasets, compute, sampling and acceleration techniques, evaluation, optimization, and productionization. Advanced texts explore theoretical guarantees, likelihoods, connections to flows and energy-based models, and frontiers such as consistency and rectified models. Many books also discuss ethics and safety, including bias, copyright, and watermarking, alongside applications in creative media, design, and scientific modeling.

Filter books by their publication year. Enter the earliest year (Start) and latest year (End) to find books published within that period. Leave either field empty to search from the beginning of time or up to the present day.