Advanced Stable Diffusion with ComfyUI and SDXL
Release date:2023, August
Duration:04 h 23 m
Author:Pixovert Studio
Skill level:Beginner
Language:English
Exercise files:Yes
Do you want to learn how to create stunning images from text using the latest AI technology? If so, this course is for you!
In this course, you will learn how to use Stable Diffusion, ComfyUI, and SDXL, three powerful and open-source tools to generate realistic and artistic images from any text prompt. You will discover the principles and techniques behind latent diffusion models, a new class of generative models that can produce high-quality images in seconds. You will also learn to use ComfyUI, a graphical user interface that lets you design and execute complex Stable Diffusion workflows without coding. You will explore SDXL, the next-generation Stable Diffusion model that can generate images with more detail, resolution, and intelligence than ever before.
By the end of this course, you will be able to:
- Generate images of anything you can imagine using Stable Diffusion 1.5 and Stable Diffusion XL – SDXL
- Fine-tune and customize your image generation models using ComfyUI
- Create photorealistic and artistic images using SDXL
- Apply your skills to various domains such as art, design, entertainment, education, and more
This course is suitable for anyone with coding or machine learning knowledge interested in AI image synthesis, whether you are someone with prior knowledge of Stable Diffusion, a beginner in ComfyUI, or an Intermediate stage learner of ComfyUI who wants to know and understand more. You don’t use coding or machine learning to follow along. All you need is a computer with a GPU and an Internet connection.
The course will be suitable for students with an Nvidia RTX GPU with at least 8 GB of VRAM. Setups with less VRAM may or may not be able to complete all the steps outlined in the lectures.
Don’t miss this opportunity to unleash your creativity and learn from the best in the field. Enroll in this course today and start making your own amazing ComfyAI images!
1. Introduction
1. Demonstration
2. Introduction
2. Getting Started
1. Installation – Installing the ComfyUI version of Stable Diffusion
2. ComfyUI – Manager and Course Extensions
3. Working Alongside Automatic 1111 – Sharing Checkpoints and Other Models
3. ComfyUI Workflow Fundamentals
1. Basic Workflows and Prompts – Stable Diffusion 1.5
4. Working with Loras and Control Loras in SDXL and Stable Diffusion 1.5
1. Working with Loras Stable Diffusion 1.5
2. Working with Unorthodox Stable Diffusion SDXL Schemes
3. Working with Loras – SDXL
4. Control-Loras SDXL – an Introduction
5. Control-Loras SDXL – Depth Map
6. Control-Loras SDXL – Recolor
7. Control-Loras SDXL – Sketch
8. Control-Loras SDXL – Remix and Revision
5. Working with ControlNets
1. ControlNets SDXL – Introduction
2. SDXL ControlNet Canny
3. SDXL ControlNet Depth Map
4. ControlNets for Stable Diffusion 1.5 Introduction and Setup
5. ControlNet SD1.5 – Setup and Scribble, Lineart and Openpose
6. SDXL and Stable Diffusion 1.5 – OpenPose Editor
7. ControlNet Stable Diffusion 1.5 Using Multiple ControlNets
8. ControlNets for Stable Diffusion 1.5 Depth Map Exercise
6. Post Processing
1. Super Resolution using Latent Upscale and Generative Adverserial Networks
7. Working with T2I Adaptors and Understanding Auxiliary Downloads
1. T2i Adaptors for SDXL and Stable Diffusion 1.5 Introduction – Depth Map
2. Auxiliary ControlNet Downloads in Stable Diffusion
8. Achieving Professional Results with Embeddings and ‘Textual Inversions’
1. Embeddings and Textual Inversions in ComfyUI for SDXL and Stable Diffusion 1.5
[Udemy] Advanced Stable Diffusion with ComfyUI and SDXL.7z
[Udemy] Advanced Stable Diffusion with ComfyUI and SDXL_Subtitles.7z
Channel
