This tutorial provides an overview of diffusion models for imaging and vision, focusing on key concepts and techniques. It begins with an introduction to Variational Auto-Encoders (VAEs), explaining their structure, training, and inference processes. The tutorial then delves into Denoising Diffusion Probabilistic Models (DDPMs), detailing their building blocks, transition distributions, and the role of magical scalars like $\sqrt{\alpha_t}$ and $1 - \alpha_t$. The tutorial also covers Score-Matching Langevin Dynamics (SMLD) and Stochastic Differential Equations (SDEs), explaining their relevance to diffusion models. Finally, it concludes with a summary of the key ideas and applications of diffusion models in generative tasks. The content is structured to provide a comprehensive understanding of diffusion models, suitable for students and researchers interested in applying these models to various problems.This tutorial provides an overview of diffusion models for imaging and vision, focusing on key concepts and techniques. It begins with an introduction to Variational Auto-Encoders (VAEs), explaining their structure, training, and inference processes. The tutorial then delves into Denoising Diffusion Probabilistic Models (DDPMs), detailing their building blocks, transition distributions, and the role of magical scalars like $\sqrt{\alpha_t}$ and $1 - \alpha_t$. The tutorial also covers Score-Matching Langevin Dynamics (SMLD) and Stochastic Differential Equations (SDEs), explaining their relevance to diffusion models. Finally, it concludes with a summary of the key ideas and applications of diffusion models in generative tasks. The content is structured to provide a comprehensive understanding of diffusion models, suitable for students and researchers interested in applying these models to various problems.