4o Image Generation in ChatGPT and Sora

It's incredible that this took 316 days to be released since it was initially announced. I do appreciate the emphasis in the presentation on how this can be useful beyond just being a cool/fun toy, as it seems most image generation tools have functioned.

Was anyone else surprised how slow the images were to generate in the livestream? This seems notably slower than DALLE.

Join Sam Altman, Gabriel Goh, Prafulla Dhariwal, Lu Liu, Allan Jabri, and Mengchao Zhong as they introduce and demo 4o image generation.