Sora's video quality seems impossible so I dug into how it works under the hoodit uses both diffusion (starting with noise, refining towards a desired video) and transformer architectures (handling sequential video frames)read on 🧵 pic.twitter.com/dCJkDi33Kz— brett goldstein (@thatguybg) February 20, 2024

1/ Using AI to generate fashionAfter a bunch of experimentation I finally got DALL-E to work for video by combining it with a few other AI toolsSee below for my workflow -#dalle2 #dalle #AIart #ArtificialIntelligence #digitalfashion #virtualfashion pic.twitter.com/x3zP3fIp4G— Karen X. Cheng (@karenxcheng) August 30, 2022

stablediffusion photoshop integration (from https://t.co/MF3xz6BHVY) pic.twitter.com/oTCkMxuQ3J— suzuha X 🏴⚡🌙 (@dystopiabreaker) August 27, 2022