It might seem like generative models are going through new phases every couple of years: we heard about Transformers, then flow-based models were all the rage, then diffusion-based models… But in fact, new ideas build on top of older ones. In the “Generative AI” book, we provide an overview of the models and ideas that have led to the development of modern large language models and image generation models—including the models themselves. The book reviews variational autoencoders, Transformers, their combinations for image generation, multimodal retrieval, diffusion-based models, and more, ending with a chapter on AGI dangers and perspectives.