This course covers the principles and methods of generative artificial intelligence for synthesizing digital content across multiple modalities, including text, images, audio, and 3D/4D data. Topics include digital representations of content; probabilistic modeling and latent variable methods; supervised, unsupervised, and self-supervised learning; autoregressive generative models; variational autoencoders; generative adversarial networks; and diffusion-based generative models. The course further covers foundation models, including large language models and large-scale image generation models, as well as multimodal generative systems. Advanced topics include generative models for 3D content and motion, neural representations and neural rendering, controllable and conditional generation, evaluation of generative models, and ethical considerations of generative AI.