The Inside View cover image

5. Charlie Snell on DALL-E and CLIP

The Inside View

CHAPTER

Using VQ to Create a 3D Model

This is like image prompting where you're able to put like, uh, sort of a, a starting image into the thing. It's already gives it a bit. How does that work? Like, um, deep learning wise. Um, so it's like VQ again. Uh, there's an encoder side. So you can take in the starting image and encode it into the latency or whatever. And yeah, you can, you can make this like beautiful, beautiful hearth from AI artists science. I think many, many people on, on Discord or tweezer, are experimenting with same exact 3D model or of a person or of a sphere and seem like all

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner