Text-to-Image Ais (ITPG-GT 3020)

“Over the past few years, the unprecedented advancement in text-to-image artificial intelligence models has sparked widespread attention, discussion, and mainstream adoption of these innovative co-creative interfaces, which has resulted in novelty, excitement, and curiosity, as well as concern, anger, and insult. Alongside this, the booming open-sourced text-to-image model development contributes to expanding access to working with AI tools beyond experts, tech giants, and professional technologists. In this 14-week course, we will go over the landscape of text-to-image AIs and dive deep into some of the most well known ones (such as Stable Diffusion and its variants), to see what potential they have in terms of exploring new modes of content creation and helping us re-examine our language pattern. This will be a practice technique course – in the first half, we’ll focus on building good prompting practices, and in the second half, we’ll explore different image synthesis skills related to text-to-image AIs, use Python to train our own models to create customized visuals, and create animations from text. We’ll also discuss how such tools could intervene in the workflows of artists and technologists, what they can provide for researchers, and what are the caveats and things we should look out for when we’re creating with these AIs. Pre-requisites: Introduction to Computational Media (ICM) or the equivalent.” Prerequisite: ICM / ICM: Media (ITPG-GT 2233 / ITPG-GT 2048)

Interactive Telecommunications (Graduate)
4 credits – 14 Weeks

Sections (Fall 2024)


ITPG-GT 3020-000 (15729)
09/06/2024 – 12/11/2024 Fri
3:00 PM – 5:00 PM (Late afternoon)
at Brooklyn Campus
Instructed by Zhang, Yuguang