Channeling Creativity Through a Deeper Understanding of AI Image Generation

Abstract

AI-generated images burst onto the scene about a year ago, with tools like Stable Diffusion, Midjourney, and DALL·E 2 all making their debut in 2022. How do these models work, and how can they be used in a production setting? In this talk, we will give an overview of how models like DALL·E 2 work and how to leverage their architectures to make them truly useful tools in the creative process. Although there are differences between each specific model architecture, the takeaways from understanding this particular stack are transferable to the others.