Drew Got No Clue@lemmy.worldtoTechnology@lemmy.world•OpenAI introduces Sora, its text-to-video AI modelEnglish
461·
8 months agoThis is so much better than all text-to-video models currently available. I’m looking forward to read the paper but I’m afraid they won’t say much about how they did this. Even if the examples are cherry picked, this is mind blowing!
I can’t understand how the shadows and reflections are so accurate (not perfect, but convincing) like here or here.