Ultimate Stable Diffusion AI art Course (beginner to pro)

Name: Ultimate Stable Diffusion AI art Course (beginner to pro)
Rating: 4.5 (457 reviews)

Learn prompt, control character pose and lighting, train your own model, ChatGPT and more with Stable Diffusion!

Created byChris White

Last updated 2/2026

English

English [Auto],Korean [Auto],

What you'll learn

A systematic course to teach you how to write professional prompts and master the fundamentals of AI painting
Acquire all the relevant skills to become an AI artist
Control your character's pose, swap outfits, adjust lighting direction, and everything in your scene
Transform ordinary streetscapes into cyberpunk masterpieces
Create refined interior designs from simple sketches
Train your own model
Use ChatGPT to work for you and greatly improve work efficiency

Course content

9 sections • 61 lectures • 6h 42m total length

Course Overview2:09
Master stable diffusion and ai image generation from basics to advanced prompts, lighting, and rendering, using Google Colab and deploying locally to train models and create artworks.

Free Preview Experience: Explore Top Image Generation Models for Free9:02
Congratulations on taking the first step in the world of AI art! This is your first lecture, and to ensure quick results, we're going to show you how to try out various AI image generation models for free. In the upcoming lectures, you will learn two ways to deploy Stable Diffusion in the cloud, and then finally, we'll get to local deployment for free, and how to troubleshoot any issues you may encounter along the way.
If you ever find that any of the links stop working, just send me a message, and I'll try to update it as soon as I can.
Set Up a Professional Web UI Online (Part 1 Colab)8:15
In this lecture, we're going to learn about a professional tool, which is also the main tool for this whole course. We'll start by showing you how to run it online, and then in section 4, we'll teach you how to install it locally for free.
Set Up a Professional Web UI Online (Part 2 Runpod)5:25
If you encounter problems while using Colab, then the runpod introduced in this lecture will be a great alternative. I will show you how to run Stable Diffusion on runpod and demonstrate how to download other third-party models.
Introduction to Web User Interfaces and the Image Generation Pipeline5:38
How Diffusion Model Works in an Easy to Understand Way - Part 1: Text to Image4:56
In this lecture, we're going to talk about how Diffusion models actually work. After this, you'll have a pretty good overview of the AI image generation process, which will help you learn faster and understand what all the different parts of the web UI do in later lectures. this is also setting the stage for the ComfyUI section we're going to add in the future.
How Diffusion Model Works in an Easy to Understand Way - Part 2: Image to Image6:03
If you understood the last lecture, then this image-to-image part will be really easy to grasp. These two lectures are very important, so don't skip them. If you're still confused about anything, feel free to send me a message : )
Before Moving Forward: Get the Most Out of This Course4:26
Before moving on, watch this video to get an overview of what's coming up. This will help you maximize your learning and get the most out of the course.

what is prompt10:49
The prompt is one of the key elements at the heart of AI art. If you don't know how to write a proper prompt and simply resort to copying and pasting prompts from others, you might encounter several challenges on your journey to becoming an AI artist. As you may have heard, "Good Artists Copy; Great Artists Steal." AI art creation shares many similarities with traditional art, such as drawing inspiration, borrowing ideas, and most importantly-- practice.
basic structure fo a prompt11:41
Discover the basic structure of prompts for stable diffusion, using four modifiers: medium, subject, detail, and resolution, and learn how their order and weighting shape image results.
Intermediate structure of prompt13:30
Learn to use the artist modifier to imitate famous artists in stable diffusion. Place the modifier at the end for focus, and experiment with order to influence the result.
Advanced structure of prompt11:33
Some tips and resources9:51
Master pro prompt techniques, including combining modifiers, adjusting keyword weights, and using seeds in stable diffusion. Explore the prompt builder and inspiration sites to refine prompts.

Install Stable Diffsuion8:16
While using the "git pull" command to keep the web UI up to date can be beneficial in terms of accessing new features and bug fixes, it's important to consider potential issues that might arise from new versions. Just like with the latest versions of Apple's iPhone software, there can be unforeseen bugs or compatibility issues.
TroubleShooting9:26
We will talk about how to resolve some common issues encountered when deploying StableDiffusion locally.
Update: Overcoming Hardware Limitations: Optimization Tips for Low-End PC2:06
If you find that the webui is generating images too slowly, or if you're encountering problems while deploying the webui, such as issues with git or python, you can use Forge, which we're introducing here, to solve these problems. This is because its one-click installation package already includes git and python. I hope this allows all of you to freely use Stable Diffusion to generate images!

Stable Diffsuion WebUI16:29
After I finished recording this course, there was an update to the web UI of "Automatic1111." The interface now has some minor differences in appearance compared to what was covered in the course, but the core functionalities remain largely unchanged.
Pro tip for previous lecture5:05
This lecture is mainly for those who have already used Stable Diffusion before. If you're a complete beginner, I recommend finishing the current section first before diving into this one. If you don't quite understand the VAE or Lightning model mentioned here, feel free to skip ahead and continue with the later content. I'll keep adding more lectures like this to help you learn more.
Let's enhance the details of the face you generated5:11
Want to significantly improve the speed and effectiveness of facial detailing? This section introduces the Adetailer plugin to help you do just that.
Inpainting9:14
Learn to use stable diffusion inpainting to add and blend new content, such as a hanging lamp or medieval castle oil painting, by adjusting prompts, denoising strength, and image size.
Custom models, Lora, Embedding9:04
Learn how to use custom models, LoRa and embeddings with stable diffusion to generate anime and photoreal images, manage model files, adjust lighting, and reduce distorted limbs.
Checkpoints recommendation for AI Artists5:47
Explore top third party stable diffusion models, filter checkpoints, choose SD 1.5 and Sdcl bases, and select deliberate for versatile, unique art; learn prompts, sampling, and control net tips.
Expand your artwork10:37
Expand your images using open out paint by enabling the API and applying prompts, brushes, and image-to-image tools to generate and refine content beyond the original frame.
Enhance the clarity of your work7:16
Update: Memory-Saving Techniques for Stable Diffusion5:50
Discover memory-saving techniques for stable diffusion, including Nvidia system memory fallback, enabling Fp8 in the web UI, and compressing models with a batch converter to save disk space.
Introduction to the Flux Model8:07
In this lecture we're going to use the flux model locally. Using the flux model is pretty similar to using regular Stable Diffusion models, it supports text-to-image, image-to-image, and inpainting. It's just that forge doesn't support controlnet for flux yet.

Brief introduction to this controlNet section5:06
Learn how control net enhances stable diffusion by guiding image generation through a preprocessor-to-model workflow, configuring control weight, start and end steps, and multi-layer control nets in the web UI.
Learn how to control the pose of your character10:26
Learn to control your character's pose in stable diffusion with the Control Net extension, using an open pose model and reference images.
Let's turn a regular street view into cyberpunk style artwork9:15
Turn a city street reference into a cyberpunk artwork using stable diffusion, control net depth, and iterative prompts to balance fidelity and creative variation through inpainting refinements.
Generate high quality interior design based on a blank space6:38
learn to generate high quality interior design renderings from a blank space using stable diffusion, with prompts and control nets, plus lighting adjustments to create balanced compositions.
Generate realistic models and change clothes freely9:29
Generate a photorealistic model and freely change clothes using stable diffusion, control net, and open pose techniques to create market-ready fashion imagery.
Learn how to control the lighting of your artworks13:53
Learn to control lighting in stable diffusion art by loading canyon depth and control net models, using canny and image-to-image prompts, and painting light maps in Affinity Photo.
Update: Use Instant-ID for quick face swap6:28
Develop quick face swap skills using instant ID with two control net units, using online tools and a local web UI, guided by Stable Diffusion models and SD 1.5 compatibility.
Use Face-ID for Quick Face Swap (SD1.5 and SDXL)3:12
Master quick face swaps in stable diffusion using face-id with SD 1.5 or SDXL, leveraging control net and auto type preprocessor for realistic, reference-image guided outputs.

New ComfyUI Section Overview 20252:06
Explore comfy UI's node-based layout for creating AI art, a flowchart of connected steps. Install the desktop version and master basic and advanced workflows, building on automatic web UI concepts.
Installing New ComfyUI Desktop2:25
Install the comfy UI desktop, create a folder on a drive with at least 20 GB free, let the GPU auto-detect, note app data path, and manage models via downloads.
ComfyUI Accessing Models from other Locations4:14
learn to access models from other folders in comfy ui by editing the config, restarting the app, and building a node-based diffusion workflow to generate images.
ComfyUI Building a Text-to-Image Workflow from Scratch5:09
Learn to build a text-to-image workflow in ComfyUI from scratch, starting with the K sampler and linking checkpoint loader, text encoder, and prompts. Decode images in latent space for preview.
How to Add and Use a New Model in ComfyUI2:11
Learn how to add and use a new model in comfyui, refresh models, review description page parameters, adjust the k sampler, generate images, and save your workflow with ctrl+s.
ComfyUI Image-to-Image From Doodles to Stunning Visuals2:47
ComfyUI Building an Image-to-Image Workflow from Scratch5:02
ComfyUI Keeping Your Nodes Organized and Easy to Read2:27
Organize your ComfyUI node graphs by grouping prompts and image nodes, renaming, coloring groups, and managing image-to-image workflows.
Group Nodes in ComfyUI Streamlining Your Workflows3:18
Master group nodes in ComfyUI to streamline complex node setups into clean, reusable modules like prefabs in Unity, using ctrl+a, convert to group, name img two img, and manage groups.
ComfyUI Most-Used Shortcuts and Efficiency Tips4:01
Master ComfyUI shortcuts to boost efficiency: bypass and mute nodes, focus mode with fit view, and customize render modes and key bindings, including opening the outputs folder.
ComfyUI Manager Installing Custom Nodes and Using the Image Comparer Node2:52
ComfyUI Inpainting Adding Sunglasses to Our Cyberpunk Hacker4:04
Learn inpainting with comfy to extend image-to-image workflows, paint masks in the mask editor, set latent masks, adjust de-noise, and craft cyberpunk hacker sunglasses.
ComfyUI How to Use Lora and Multiple Loras6:17
Set up Laura files and paths, edit the config, and restart comfy UI. Add a Lora node, connect it from checkpoint to prompt and K sampler, and explore using loras.
ComfyUI Connecting Off-Screen Nodes Quickly and Easily2:15
Auto-Organizing Your Workflow in One Click1:46
Install and activate workflow auto arrange node, select the latest version, and restart. Organize the workflow with float left or right, generate an image, and adjust preview height and spacing.
ComfyUI Set Up ControlNet - Part 1 Extracting Image Data with Preprocessor5:32
ComfyUI Set Up ControlNet - Part 2 Preparing ControlNet Models2:08
ComfyUI Set Up ControlNet - Part 3 Apply ControlNet7:36
Apply controlnet in comfyui by placing the controlnet node between text encode and k sampler, using a union model, and tuning strength 0.6–1 to shape outputs with depth or canny.
ComfyUI Running Flux with ease3:14
Run the flux model in ComfyUI by configuring the model path, adding a flux guidance node, and setting cfg to 1.0 with a chosen sampler and scheduler.
ComfyUI Running Flux GGUF Model for Low VRAM Card3:39
ComfyUI Integrating ControlNet into Your FLUX Workflow5:02
ComfyUI AI Video Generation with Wan2.18:42
ComfyUI How to Create Video From a Starting Image with Wan2.15:05
Download the image to video model and the clip vision model, place them in the right folders, and build the workflow by adding the node and wiring the inputs.

Let's use newest SDXL 1.0 base model and refiner model!8:27
Introduce how to use online services and how to use newest SDXL base model and refiner model on Automatic1111, and compare the effect of refiner model.
Learn how Stable Diffusion works in a fun way4:16
Explore how stable diffusion powers a web user interface, using a seed, text encoder, and samplers to craft image to image revisions with denoising.

Requirements

No programming experience needed
Internet Connection
Google account
A computer with a minimum of 4GB dedicated graphics memory

Description

Hello everyone, welcome to our course. This is a comprehensive, beginner-to-expert course focused on StableDiffusion. Whether you've had experience with AI image generation or used any AI image generation tools before, you can easily learn from this course.

I'll teach you how to use Google Colab to generate Stable Diffusion images. We'll explore a crucial concept—prompt, what it is, how it's structured, and how to create a good prompt. We'll start with the basics of prompt and progress to advanced prompts, learning about lighting, rendering, and special prompt techniques. Next, we'll dive into what StableDiffusion is and how to deploy it locally, learning about its features and some incredibly useful extension modules. We'll also learn how to use third-party models and train your own model. You'll be able to create characters in any pose, add realistic and adjustable lighting, create your own fashion models and swap their outfits, transform ordinary street scenes into cyberpunk-style artwork, generate exquisite interior designs from an empty room, quickly swamp character's faces, and use ChatGPT to help us create high-quality prompts, among many other valuable skills. By the end of this course, and with the proficient application of the techniques taught, you'll confidently create almost any artwork you can imagine and apply them to your projects.

Fasten your seatbelt and get ready. Let's get started!

Who this course is for:

Anyone interested in learning AI painting or AI image generation
People aspiring to become AI artists

Ultimate Stable Diffusion AI art Course (beginner to pro)

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 2min

Your first AI Image7 lectures • 44min

The magic of prompt5 lectures • 57min

Install Stable Diffusion on your PC3 lectures • 20min

Basic Stable Diffusion workflow and add your final touch10 lectures • 1hr 23min

Control the pose, lighting, clothes, swap faces, and even more8 lectures • 1hr 4min

Train your own model and use ChatGPT to do the heavy lifting2 lectures • 27min

New ComfyUI Section in 202523 lectures • 1hr 32min

Future course update2 lectures • 13min

Requirements

Description

Who this course is for: