Generative Deep Learning by David Foster is a practical book for machine-learning engineers and data scientists who want to learn how to re-create some of the most impressive examples of generative deep learning models. The book covers various techniques such as variational autoencoders, generative adversarial networks (GANs), encoder-decoder models, and world models. The author demonstrates the inner workings of each technique and provides tips and tricks to make models learn more efficiently and become more creative. The book also includes code examples using Pytorch and a code repository on Github.