Generative AI · Ebook

Image Generation: From Pixels to Diffusion Models

by Shriira Press

A comprehensive, self-contained guide to how machines learn to create images — from the first generative networks to the diffusion models and text-to-image systems behind today's AI art tools. Like its companion volume on machine learning, this book blends intuition, mathematics, and runnable code, building from first principles up to Stable Diffusion, ControlNet, and beyond.

Contents

1. 1Preface
2. 2Chapter 1 — What Is Image Generation?
3. 3Chapter 2 — Images, Probability, and the Generative Problem
4. 4Chapter 3 — Neural Building Blocks for Generation
5. 5Chapter 4 — Autoencoders and Variational Autoencoders
6. 6Chapter 5 — Generative Adversarial Networks
7. 7Chapter 6 — Autoregressive and Discrete-Token Models
8. 8Chapter 7 — The Diffusion Idea: Forward and Reverse
9. 9Chapter 8 — Training and Sampling Diffusion Models
10. 10Chapter 9 — Conditioning and Guidance
11. 11Chapter 10 — Latent Diffusion and Modern Architectures
12. 12Chapter 11 — Anatomy of a Text-to-Image System
13. 13Chapter 12 — Control, Customization, and Editing
14. 14Chapter 13 — Evaluation, Ethics, and Deployment
15. 15Appendix A — Notation and Symbols
16. 16Appendix B — Further Reading