Lumiere is a space-time diffusion research model that demonstrates state-of-the-art text-to-video generation, by deploying both spatial & (importantly) temporal down- and up-sampling and leveraging a pre-trained text-to-image diffusion model. Learn more→ https://t.co/QAMgC4TmBL pic.twitter.com/iAYsgIpbDP
— Google AI (@GoogleAI) 6 février 2024
Lumiere is a space-time diffusion research model that demonstrates state-of-the-art text-to-video generation, by deploying both spatial & (importantly) temporal down- and up-sampling and leveraging a pre-trained text-to-image diffusion model. Learn more→ https://
goo.gle/47WX6C2



