In How Diffusion Models Work, you will gain a deep familiarity with the diffusion process and the models which carry it out. More than simply pulling in a pre-built model or using an API, this course will teach you to build a diffusion model from scratch.
In this course you will:
1. Explore the cutting-edge world of diffusion-based generative AI and create your own diffusion model from scratch.
2. Gain deep familiarity with the diffusion process and the models driving it, going beyond pre-built models and APIs.
3. Acquire practical coding skills by working through labs on sampling, training diffusion models, building neural networks for noise prediction, and adding context for personalized image generation.
At the end of the course, you will have a model that can serve as a starting point for your own exploration of diffusion models for your applications.
This one-hour course, taught by Sharon Zhou will expand your generative AI capabilities to include building, training, and optimizing diffusion models.
Hands-on examples make the concepts easy to understand and build upon. Built-in Jupyter notebooks allow you to seamlessly experiment with the code and labs presented in the course.
Status: AI Personalization
AI Personalization
Status: Algorithms
Algorithms
Intermediate·Project·2 hours
Featured reviews
5.0
·Reviewed Nov 24, 2023
Janet Zhou was able to explain simply, not waste too much time on details, yet give opportunity to go much deeper into code. I would like to see a next level course on same topics.
4.0
·Reviewed Dec 10, 2024
No assignment or real assessment to start from scratch. It's just a review of a premade model.
5.0
·Reviewed May 7, 2024
Excellent content..! Small though Complete in itself..!!
5.0
·Reviewed Sep 12, 2023
Very clean code while going into implementation detail
5.0
·Reviewed Apr 8, 2024
It seems like there is a problem with the caption not matching the video slightly.
5.0
·Reviewed Oct 14, 2023
Very Good for getting the starting feel of Diffusion Models
5.0
·Reviewed Oct 16, 2023
An amazing and excellent course for Stable Diffusion Models and how it works from scratch.
4.0
·Reviewed Oct 6, 2023
Course entails the basic Concepts of DDPM and DDIM Diffusion Models
5.0
·Reviewed Oct 21, 2023
Quick to-the-point insight into the workings of Diffusion nets, unet.
5.0
·Reviewed Feb 11, 2025
really to the point and great insights! highly recommend!
4.0
·Reviewed Jul 24, 2026
Thank you.The course is so good.Please do the same for DiTs, also in a little more easier way to understand .
All reviews
Showing: 20 of 42
All Learners
All Stars
Most Helpful
Ł
Łukasz
5.0
·Reviewed Dec 28, 2023
The only pity is that the course is so short. It definitely has a potential to become something larger - there already is a GAN specialization, however there is still much to cover. Fingers crossed that expansion of courses such as this one will happen soon!
T
Tom
5.0
·Reviewed Nov 25, 2023
Janet Zhou was able to explain simply, not waste too much time on details, yet give opportunity to go much deeper into code. I would like to see a next level course on same topics.
G
Guangyao
5.0
·Reviewed Mar 10, 2024
Excellent course. The instructor clearly explained the basics of diffusion models and brought us through a full fun example of generating images with those models :)
G
Gopinathan
5.0
·Reviewed Oct 17, 2023
An amazing and excellent course for Stable Diffusion Models and how it works from scratch.
S
Suesarn
5.0
·Reviewed Apr 9, 2024
It seems like there is a problem with the caption not matching the video slightly.
X
Xavier
5.0
·Reviewed Oct 22, 2023
Quick to-the-point insight into the workings of Diffusion nets, unet.
P
Palash
5.0
·Reviewed Oct 15, 2023
Very Good for getting the starting feel of Diffusion Models
S
Shashvat
5.0
·Reviewed Feb 12, 2025
really to the point and great insights! highly recommend!
B
Bhaveshkumar
5.0
·Reviewed May 8, 2024
Excellent content..! Small though Complete in itself..!!
M
Maxarram
5.0
·Reviewed Dec 4, 2023
Ushbu kursdan oʻzimga kerakli bilimlarni oldim. Raxmat
I
Imry
5.0
·Reviewed Sep 13, 2023
Very clean code while going into implementation detail