Explore a comprehensive PyTorch implementation of Diffusion Models in this 22-minute tutorial video. Dive into the world of generative models, including popular examples like DALL-E, Imagen, and Stable Diffusion. Learn to code an unconditional version and train it step-by-step. Discover two key improvements: classifier-free guidance and exponential moving average. Implement these updates and train a conditional model on CIFAR-10, comparing various results. Follow along with code examples, gain insights from relevant research papers, and understand concepts like timestep embedding. Perfect for those interested in state-of-the-art machine learning techniques and their practical applications in image generation.
Overview
Syllabus
Introduction
Recap
Diffusion Tools
UNet
Training Loop
Unconditional Results
Classifier Free Guidance
Exponential Moving Average
Conditional Results
Github Code & Outro
Taught by
Outlier
Related Courses
-
Advanced Generative Adversarial Networks (GANs)
-
Diffusion Models Beat GANs on Image Synthesis - ML Coding Series - Part 2
-
OpenAI GLIDE - Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
-
ControlNet: Adding Conditional Control to Text-to-Image Diffusion Models
-
Reflected Diffusion Models: Principled Data Constraints in Generative Modeling
-
Diffusion Models Beat GANs on Image Synthesis - Machine Learning Research Paper Explained
Reviews
5.0 rating, based on 1 Class Central review
-
Very quick learning Diffusion Models. Initially I was skeptical about the time duration. Once the course started, I was convinced it is going to be good.
