In this workshop, you will learn about diffusion models, a powerful type of generative model that can generate new, realistic data by progressively adding and removing noise. We'll begin by exploring what diffusion models are, how they work through a forward process that corrupts data with noise, and a reverse process that denoises and reconstructs clean samples. Next, we'll dive into the advantages of diffusion models compared to other generative models like GANs and VAEs, highlighting their stable training, ability to generate high-quality outputs, and flexibility. Lastly, you'll discover the wide range of real-world applications for diffusion models, from image generation and super-resolution to video prediction, anomaly detection, and more, showcasing their versatility across fields such as manufacturing, medical imaging, and entertainment.