Introducing GenAI Space-Time U-Net architecture!
Check out the kind in the comments π below!
Lumiere, a text-to-video diffusion model, uses Space-Time U-Net to create videos that are both realistic and coherent. By processing videos in multiple space-time scales, our model achieves state-of-the-art text-to-video generation results.
This is an exciting breakthrough in video synthesis. Some of these examples in the site are fairly amazing even if there are still some fragments with the eyes.
SpaceTime VideoSynthesis Innovation AI Technology generativeai
π‘πΌππΆπ°π²: The views expressed in this post are my own. The views within any of my posts or articles are not those of my employer or the employers of any contributing experts. ππΆπΈπ² π this post? Click ππ΅π² π―π²πΉπΉ icon π for more!
