Learn Generative AI w SDXL Stable Diffusion & ComfyUI UPDATE
What you'll learn
- Install ComfyUI and the Stable Diffusion Models
- Understand SDXL (Stable Diffusion XL) models and workflows
- Understand the key features of ComfyUI
- Understand the core features of Stable Diffusion
- How to use the SDXL Refiner correctly
- Recognise the important of AI models and interactions between models
- Develop sophisticated prompts and refine them
- How to curate your Stable Diffusion models
- Where to find ComfyUI workflows and how to install them
- How to use ComfyUI extensions like the ComfyUI manager
- Using Stable Diffusion to replicate features of Photoshop's Generative Fill
- Working with complex time related prompts
- Working with multiple stage workflows
Requirements
- No programming experience needed, but experience with 'node-based editors' is an advantage
- An Nvidia graphics card with at least 4GB of memory improves performance hugely, but is not essential
- A computer or laptop running Windows 10 or later
- A good command of English - there are no captions at present on the course
- The software is free and open source - bring an open mindset!
Description
For Beginner's who are looking to dive into Generative AI - making images out of text.
UPDATED 2025
ComfyUI is an advanced node-based UI that utilizes Stable Diffusion. It allows you to create customized workflows such as image post-processing or conversions. It is a powerful and modular stable diffusion GUI with a graph/nodes interface. This UI lets you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart-based interface. It is an extremely powerful Stable Diffusion graphical user interface and the graph/nodes interface is ideal for advanced users as it gives precise control over the diffusion process without any coding being required.
ComfyUI is an amazing tool that can help you achieve your goals with ease and precision. Its advanced features and user-friendly interface make it a top choice for anyone looking to work with Stable Diffusion. Give it a try and see for yourself how it can help you achieve your goals!
System Requirements
A graphics card from Nvidia with at least 4GB of VRAM hugely improves performance of this software. More video card VRAM than this is recommended. Running without an Nvidia GPU is possible but will be extremely slow.
Stable Diffusion is a deep learning, text-to-image model that was released in 2022. It is primarily used to generate detailed images conditioned on text descriptions, but it also possesses powerful compositional and post processing potential.
Prompts are at the core of using Stable Diffusion and other Generative AI models.
Prompt engineering is the art of communicating with a generative AI model using natural language. Prompt engineering has been described as the number "one job of the future" at the World Economic Forum and as "an amazingly high-leverage skill and an early example of programming in a little bit of natural language" by Sam Altman, one of the founders of Open AI.
It involves crafting input text that instructs the model on what to do and how to do it, as well as providing, cues, and supporting content to guide the model’s output. Prompt engineering is a valuable skill for constructing intelligent outputs with generative AI, as it can unlock the potential of large language models (LLMs) that have been trained on massive amounts of data.
The course will touch lightly on theory and focus on practicalities, but the theory is always a foundational aspect of the material explored here.
Attention to detail and open-mindedness are essential in Generative AI and both are encouraged throughout the course. The course aims to provide a solid foundational understanding of the software that will act as a launchpad for further exploration.
Who this course is for:
- Designers
- AI enthusiasts who want to understand how generative AI plays within the world of art
- Existing Stable Diffusion users who want to learn new methods, (but this is NOT a transfer course for A1111 users - Comfy is NOT A1111!)
- Artists looking to incorporate generative AI into their set of tools
Instructor
Pixovert specialises in online tutorials, providing courses in creative software and has provided training to millions of viewers.
Subject matter includes Canva, the Adobe Creative Cloud – Photoshop, Premiere Pro, After Effects and Lightroom. In addition to this Pixovert covers photography and design related content including Gimp and Darktable, and advice for professions in the creative fields.