Generative learning (GL) has emerged as an essential tool for data processing and network optimization in the broad area of next-generation communication systems. Generative Learning for Wireless Communications: Fundamentals and Applications provides a comprehensive and systematic tutorial for applying generative learning models to wireless communications. It explains the core concepts of state-of-the-art generative learning models, including generative adversarial nets, variational autoencoder, and other advanced models, such as transformers and diffusion models, and then shows their application to specific areas in wireless communications. Areas include physical networking, data transmission, edge computation, distributed learning, semantic communications, and other emerging fields in the next-generation wireless communications. To provide guidance on how to use GL techniques, each chapter includes a case study and an algorithm design for a realistic application. The book concludes with a discussion of the critical challenges of today and promising future directions of GL in wireless communications.