This repository accompanies the O’Reilly book teaching machines to paint, write, compose, and play through generative deep learning. It provides Jupyter Notebook implementations covering variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, energy-based models, diffusion models, Transformers, and multimodal approaches. The code is designed to run with Docker and includes TensorFlow implementations alongside dataset setup for hands-on learning.