Stable Diffusion Masterclass - Theory, Code & Application

Stable Diffusion Masterclass - Course Overview

Welcome to this course on Diffusion Models! My name is Mandy, and I'll be your instructor for the course.

In this course, we'll be learning all about latent diffusion models! These are the models responsible for the huge rise in AI art generation that have taken the world by storm, allowing individuals everywhere to create compelling images and unique works of art!

Not only will we be learning how exactly these models work, but we'll also be getting hands on experience with creating our own AI generated images using these models. We'll be using the open source model, Stable Diffusion and popular tools like the Automatic111 Stable Diffusion Web UI, and the Kohya GUI to do so.

We'll also be exploring how to work with these models in code using the HuggingFace Diffusers library!

Not only will we learn all about these models how to use them to generate compelling images, but we'll also learn how to train the models on new subjects, like ourselves!

About the Course

Our goal in this course is to gain a fundamental understanding for how exactly latent diffusion models work and how we can use them to generate images of anything we'd like. These models are made up of several components, and we'll be exploring them all! We'll also learn about the data preprocessing steps, how these models are trained, as well as how to easily work with these models in both a UI and in code.

As for how we'll approach all of these topics, we'll first be gaining a full understanding for how exactly image generation works with diffusion models, ironing out all the technical details along the way. Then we'll be able to apply our newly gained understanding to actually begin working with these models to generate compelling images!

Be sure to check out the full syllabus on the course page to see all the topics we'll be covering in this course. Here, we have a quick overview of some of the main topics.

Course Prerequisites

Now let's discuss the prerequisites that are required for this course.

• Understanding of deep learning and neural networks
• Basic coding skills
• Basic Python experience
• PyTorch API experience (recommended, not required)
• General knowledge about generative models and NLP (recommended, not required)
• General understanding of generative AI art (optional)

If you are brand new to deep learning, then it is recommended that you start with our Deep Learning Fundamentals course first, as we'll be building on these fundamental concepts to form our understanding of how we can use artificial neural networks as diffusion models to generate images.

The Deep Learning Fundamentals course will teach you everything you need to know to get acquainted with all the major deep learning concepts. You can then take your newly gained knowledge from that course, and come to apply it in this one.

Later in the course, we'll jump into code, implemented using the HuggingFace Diffusers API and PyTorch, to apply what we've learned about diffusion models. We'll be going step-by-step through the code when we get there, but in regards to coding prerequisites, some basic coding skills and Python experience are needed.

It's also recommended, but not necessarily required, to have experience with a neural network API, like PyTorch. You can check out our PyTorch course to get acquainted with the library before we implement our code projects later in the course.

Note that we'll touch on some text preprocessing and the usage of word embeddings in this course. We'll additionally draw a couple of comparisons to other generative models like GANs. It's alright if you're not already totally familiar with these concepts, as it's not required that you fully understand them before taking this course. To gain a better understanding of these topics, however, we recommend checking out our NLP Intro for Text course as well as our GANs Intro course to get acquainted with these topics.

Finally, if AI art is a totally new concept to you and you haven't yet heard of models like Stable Diffusion, we recommend getting familiar with this topic by visiting our AI Art for Beginners Crash Course. This course will give you a understanding of what AI art is, how it's created, and how to create your own AI art.

How to register for the course

Registration consists of two steps: creating an account on deeplizard.com and purchasing the course.

1. Create a deeplizard account.
1. Click the Login link on the top right of any page of deeplizard.com.
2. Click create account.
3. Enter a valid email address and password.
4. Enter the verification code sent to your email address.
2. Purchase the course.
1. Ensure you're logged in to deeplizard.com.
2. Browse to the course page.
3. Click the Enroll button.
4. Agree to the Terms and Conditions.
5. Enter your payment details. If you have a discount code, you may enter it here.
6. Upon successful payment, the course will become unlocked, and you may view the full contents.

For more information and to view the full course syllabus, be sure to see the course page. We hope you enjoy the course!