55:51Building The World's Best Image Diffusion Model
Suhail Doshi explains how Playground shifted from a general image generator toward a visual design tool built around templates and conversational editing. The talk describes Playground v3’s focus on prompt understanding, accurate text rendering, and detailed image control, along with the architectural changes the team made to support those goals. Doshi discusses learning from user behavior, choosing commercially useful design tasks, and how close prompt adherence can complicate aesthetic evaluations. He also reflects on earlier ventures, research priorities, and why reaching state of the art requires sustained attention to small details.