Hacker News new | ask | show | jobs
by bufferoverflow 492 days ago
Isn't modeling and animating the hardest part anyway? You're saving some time on texturing and lighting (which is still good, don't get me wrong).

But the whole premise of AI video is that you're basically directing, and the model does all the hard parts for you.
1 comments
TobiasEnholmX 492 days ago
Yeah, modeling and animating used to be a huge bottleneck, but with tools like image-to-3D and improving AI animation models, it's getting easier and faster. The goal here isn’t to replace animation but to use 3D as a guide, so AI doesn’t have to guess everything from scratch. In this workflow, you don’t even need animations—just static 3D models. The output is a single image that gets passed to a video model, which handles the motion.
link
bufferoverflow 492 days ago
Oh, I didn't realize you were feeding static 3D scenes to it, basically only the first frame.

That makes it a lot more useful.

link