Architecture After AI
University of Texas at Austin
Symposium February 3
Exhibit Jan 30—February 24
In certain circles, 2022 will be remembered as the Year of the Text-to-Image Model. Last April, OpenAI launched DALL-E 2, an update to DALL-E released the previous year, which produces highly detailed and often surrealistic images from text descriptions in a matter of seconds. (The name is a portmanteau of the Pixar character WALL-E and the artist Salvador Dalí). Fast on DALL-E 2’s heels came Stable Diffusion, Midjourney, Imagen, and other “deep learning” models that essentially do the same thing. The computer architectures that enable these platforms are not new but were previously only used
→ Continue reading at The Architect's Newspaper
