Text-to-image with Stable Diffusion

Over the past year, 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. Among all these open-sourced treasures, the recently-released Stable Diffusion text-to-image model by stability.ai outperforms for its fast training speed, highly customizable settings, and impressive generating quality. 

In this workshop, we will go over the landscape of text-to-image AIs and dive deep into Stable Diffusion (SD), to see what potential they have in exploring new modes of content creation and helping us re-examine our language pattern. We’ll 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.

Presenters:

Tong Wu

Tong Wu is a creative technologist and multimedia artist raised on the Internet. She now co-exists with her digital doubles in New York and the Chrome browser. Wu's art research focuses on cyberculture, the digital system, and how "individuals" form relationships with their overpopulated avatars in the era of digital where artificial intelligence models heavily intervene in our daily lives.

Yuguang Zhang

Yuguang (YG) Zhang is a new media / AI artist. His current practice, which incorporates interactive media, installation, and performance, explores the connections we make with the ubiquitous AI systems around us, the surprises and struggles we have when we surrender our authorship to intelligent algorithms, and the cultural & ethical shifts that come along.

Host or Publisher CultureHub