Top
Best
New

Posted by avaer 6 hours ago

Waypoint-1: Real-Time Interactive Video Diffusion from Overworld(huggingface.co)
33 points | 8 comments
dsrtslnd23 2 minutes ago|
10,000 hours training data seems quite low for a world model?
roskelld 1 hour ago||
The context seemed to last a few seconds. I went from a mock up screenshot of a fantasy video game, complete with first person weapon. Then as I moved forward the weapon became part of the scenery and the whole world blurred and blended until it became some sort of sci-fi abstract space. Spinning the camera completely changed look and style.

I ended up with a UI that closely resembled the Cyberpunk 2077 one complete with VO modal popup. I guess it must have featured a lot in the training data.

Really not sure what to make of this, seems to have no constraints on concept despite the prompt (I specifically used the word fantasy), no spatial memory, no collision, or understanding of landscape features in order to maintain a sense of place.

avaer 50 minutes ago||
Accurate to my experience hacking on this model today, but I don't think anyone's blowing smoke about it.

Thinking back to where GPT-3 was 5 years ago, I can't help but be a little bit excited. And unlike GPT-3 this is Apache.

sampton 23 minutes ago||
It's an acid dream.
avaer 47 minutes ago||
If you think this is cool you might also be interested in https://github.com/MineDojo/NitroGen which is kind of the opposite (and complimentary).
lcastricato 16 minutes ago||
Hi,

Louis here. CEO of overworld. Happy to answer questions :)

Plankaluel 1 hour ago||
An RTX 5090 for 20-30fps for the small model: That is not as unreasonable as I had feared :D
khimaros 1 hour ago|
this is like an open weights version of DeepMind's Genie