Introduction to Diffusion Models

Focused View

Maxime Vandegar

8:03:34

169 View

1 - Introduction

1 - Introduction.mp4

17:21

2 - Initial paper on Diffusion Models

2 - Forward Diffusion process.mp4

11:20

3 - Forward Diffusion process implementation.mp4

19:34

4 - Diffusion process tricks.mp4

07:22

5 - Diffusion process incorporation of the tricks in the implementation.mp4

11:42

6 - Diffusion process visualization.mp4

09:54

7 - Reverse process.mp4

08:28

8 - Reverse process implementation.mp4

04:33

9 - Architecture of the model.mp4

18:37

10 - Reverse process sampling.mp4

09:46

11 - Reverse process visualization.mp4

04:21

12 - Training equations part 1.mp4

19:43

13 - Training equations part 2.mp4

11:27

14 - Training equations implementation part 1.mp4

10:52

15 - Training equations implementation part 2.mp4

11:41

16 - Implementation of the training loop.mp4

07:53

17 - Training on GPU.mp4

10:34

18 - Correct typo.mp4

01:17

19 - Reproduction of a Figure from the paper Analysis of the results.mp4

03:06

3 - Denoising Diffusion Probabilistic Models

20 - Review of the paper.mp4

22:12

21 - Time embedding.mp4

03:51

22 - Pseudocode.mp4

04:55

23 - UNet Implementation time embedding.mp4

13:50

24 - UNet Implementation downsampling.mp4

13:14

25 - UNet Implementation upsampling.mp4

06:44

26 - UNet Implementation ResNet part1.mp4

14:14

27 - UNet Implementation ResNet part2.mp4

21:03

28 - UNet Implementation ResNet part3.mp4

03:51

29 - UNet Implementation Attention Mechanism part1.mp4

08:34

30 - UNet Implementation Attention Mechanism part2.mp4

01:16

31 - Finishing the UNet Implementation part1.mp4

18:58

32 - Finishing the UNet Implementation part2.mp4

06:35

33 - Finishing the UNet Implementation part3.mp4

03:23

34 - Finishing the UNet Implementation part4.mp4

15:02

35 - Finishing the UNet Implementation part5.mp4

05:51

36 - Denoising Diffusion Probabilistic Models implementation.mp4

06:27

37 - Denoising Diffusion Probabilistic Models training.mp4

08:22

38 - Denoising Diffusion Probabilistic Models sampling.mp4

12:05

39 - Denoising Diffusion Probabilistic Models utils.mp4

11:17

40 - Denoising Diffusion Probabilistic Models training loop.mp4

05:14

41 - Denoising Diffusion Probabilistic Models visualization.mp4

06:51

42 - Denoising Diffusion Probabilistic Models training on GPU.mp4

06:30

43 - Analysis of the results.mp4

01:46

4 - Inpainting

44 - Inpainting with Diffusion Models explanation.mp4

12:02

45 - Inpainting with Diffusion Models implementation.mp4

22:16

5 - Animating Diffusion Models

46 - Animations part1.mp4

11:41

47 - Animations part2.mp4

09:27

48 - Animations part3.mp4

06:32

Description

Diffusion Models from scratch using PyToch | In depth break down of Stable Diffusion and DALL-E

What You'll Learn?

How Diffusion Models work
Implementation of Diffusion Models from scratch using PyTorch
In depth understanding of inpainting with Diffusion Models
Deep analysis of Stable Diffusion: opening the black box
Making great animations with Diffusion Models
Review of impactful research papers

Who is this for?

To engineers and programmers

To students and researchers

To entrepreneurs, CEOs and CTOs

Machine Learning enthusiast

What You Need to Know?

Basic programming knowledge

Basic Machine Learning knowledge

More details

Description
Welcome to this course on Diffusion Models!

This course delves into the fascinating world of diffusion models, starting from the initial research paper and advancing to cutting-edge applications such as image generation, inpainting, animations, and more. By combining a theoretical approach, and hands-on implementation using PyTorch, this course will equip you with the knowledge and expertise needed to excel in this exciting field of Generative AI.

Why choose this Diffusion Models Course?

From Theory to Practice: This course begins by dissecting the initial research paper on diffusion models, explaining the concepts and techniques from scratch. Once you have gained a deep understanding of the underlying principles, we will reproduce results from the initial diffusion model paper, from scratch, using PyTorch.
Advanced Image Generation: Building upon the foundational knowledge, we will dive into advanced techniques for image generation using diffusion models.
Inpainting and DALL-E-like Applications: Discover how diffusion models can be used for inpainting, enabling you to fill in missing or damaged parts of images with stunning accuracy. After this session, you will have a deep understanding of how inpainting works with models such as Stable Diffusion or DALL-E, and you will have the knowledge needed to modify it to your needs.
Animation Mastery: Unleash your creativity and learn how to create captivating animations using diffusion models.
Dive into Stable Diffusion: Gain an in-depth understanding of Stable Diffusion and its inner workings by reviewing and analyzing the source code. This will empower you to utilize Stable Diffusion effectively in your own industrial and research projects, beyond just using the API.
Stay Informed with Impactful Research: Stay up to date with the latest advancements in diffusion models by reviewing impactful research papers. Gain insights into the cutting-edge techniques and applications driving the field forward, and expand your knowledge to stay ahead of the curve. Register now to access our comprehensive online course on Diffusion Models and learn how this technology can enhance your projects. Donâ€™t miss this opportunity to learn about the latest advances in Generative AI with Diffusion Models!

Register now to access our comprehensive online course on Diffusion Models and learn how this technology can enhance your projects.

Donâ€™t miss this opportunity to learn about the latest advances in Generative AI with Diffusion Models!

Who this course is for:
To engineers and programmers
To students and researchers
To entrepreneurs, CEOs and CTOs
Machine Learning enthusiast

User Reviews

Rating

average 0

Total votes0

Focused display

Ingénieur fraîchement diplômé, je suis actuellement chercheur à l'université de Stanford et scientifique collaborateur au CERN. Mes recherches combinent l'intelligence artificielle (principalement le deep learning) et la physique fondamentale.Durant mes études, j'ai été responsable de séances d'exercices dans plusieurs cours universitaires (mécanique des matériaux, électronique numérique, signaux et systèmes,...) et je donne régulièrement des séances de coaching avancées en Python.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.