Загрузка видео...
Не удалось загрузить видео
Wow, diffusion models (used in AI image generation) are also game engines - a type of world simulation. By predicting the next frame of the classic shooter DOOM, you get a playable game at 20 fps without any underlying real game engine. This video is from the diffusion model.
1,768,653 просмотров • 1 год назад •via X (Twitter)
Комментарии: 9

Paper and details:

Tesla can do something similar with real world video

I honestly don’t find this compelling. They obviously trained on a large corpus of games screenshots and it’s just generating the screen that probilistixally follows the current one. The issue is that this can only be achieved by having an initial game from which a corpus can be derived. If there is no game there is no corpus so where is the value add?

How does the game maintain state? When you turn around how does it know what came before?

Gives a whole new meaning to P(doom)!

So you made DOOM run inside an LLM. Just say it

So you’re saying that it shows you images based on where you’re looking? As in it only renders when observed? 👀 *Tinfoil hat intensifies*

Amazing but also supremely irritating that the source code isn’t available given that it’s based on an open source model.

Ok a few questions that i have what's the difference in power consumption between the original dos release the doom 64 bit release and the AI generated version here. Its cool but i am guessing it will come at a massive cost showing a traditional rendering will be more efficient.
