Gain insights into diffusion models, explore their workings and architecture, and learn to create images from noise using neural networks and pretrained models with practical implementations.

irprof.tar.gz

jupyter

demo

jupyter123

jupyter-copy-bgf8w1

Diffusion_model_tasks

DDPM_test

DDPM_training

Challenge_sol

Challenge

In this course, you’ll gain practical insight into the theoretical concepts associated with diffusion models, complemented by hands-on expertise in creating images from noise and training neural networks for effective image sampling.

You’ll start with the introduction to generative models, specifically focusing on how diffusion models fall under this category. You’ll dive deep into the intricacies of diffusion models, exploring their workings, architecture, and the theoretical foundations supporting them. Subsequently, various diffusion model tasks will be introduced, and you will implement them using the Diffusers library, which provides cutting-edge pretrained diffusion models. You’ll learn how to set up and train a neural network model and sample images. 

By the end of this course, you’ll understand diffusion models clearly, generate images from noise, navigate the complexities of diffusion models, and harness the full potential of generative models in diverse applications.

Introduction to Diffusion Models

Conclude your journey by revisiting what you learned.

Conclusion

Course Overview

Getting Started

Image Creation from Scratch

Wrapping Up

Appendix

Conclusion

Course summary