From Still to Motion: How Diffusion Models Learned to Generate Videos
Extending image diffusion to the temporal dimension — from 2D noise to coherent video, one frame at a time.
intermediate~4 hours3 notebooksThe Flipbook IntuitionWhat Makes Video Different from Images?The Naive Approach — Why Frame-by-Frame FailsExtending the Diffusion Framework to VideoThe Architecture — How Neural Networks Learn Space and Time
Curator of this Module
Dr. Rajat Dandekar
Course Instructor
Dr. Rajat Dandekar is a researcher and educator specializing in AI/ML, with a passion for making complex concepts accessible through intuitive explanations and hands-on learning.
Checking access…
Learning Path
Article
1
Notebook 12
Notebook 23
Notebook 3Case Study
Certificate