Generative models are widely used in many subfields of AI and Machine Learning. Recent advances in parameterizing these models using deep neural networks, combined with progress in stochastic optimization methods, have enabled scalable modeling of complex, high-dimensional data including images, text, speech, and time series. During this Birds of a Feather presentation, we will touch on these four categories of data (image, text, audio, and time series) and explore top generative models that make these types of synthetic data generation possible. Our focus will primarily be on “the coolest thing since sliced bread” – Yann LeCunn, with Generative Adversarial Networks (GANs) but also touch on transformer decoder models, like GPT-3, for generation of textual data. Last, we will investigate real world applications of each of these data fields and show how generative models can push boundaries for applications where a lack of data was prevalent.