Live data from Hacker News

Diffusion models are real-time game engines

gamengen.github.io

51–60 of 430 posts

Re: Diffusion models are real-time game engines

#51
post #2

So, this is surprising. Apparently there’s more cause, effect, and sequencing in diffusion models than what I expected, which would be roughly ‘none’. Google here uses SD 1.4, as the core of the diffusion model, which is a nice reminder that open models are useful to even giant cloud monopolies. The two main things of note I took away from the summary were: 1) they got infinite training data using agents playing doom…

Just want to clarify a couple possible misconceptions:

The diffusion model doesn’t maintain any state itself, though its weights may encode some notion of cause/effect. It just renders one frame at a time (after all it’s a text to image model, not text to video). Instead of text, the previous states and frames are provided as inputs to the model to predict the next frame.

Noise is added to the previous frames before being passed into the SD model, so the RL agents were not involved with “correcting” it.

De-noising objectives are widespread in ML, intuitively it forces a predictive model to leverage context, ie surrounding frames/words/etc.

In this case it helps prevent auto-regressive drift due to the accumulation of small errors from the randomness inherent in generative diffusion models. Figure 4 shows such drift happening when a player is standing still.

Re: Diffusion models are real-time game engines

#52
Ah finally we are starting to see something gaming related. I'm curious as to why we haven't seen more of neural networks applied to games even in a completely experimental fashion; we used to have a lot of little experimental indie games such as Façade (2005) and I'm surprised we don't have something similar years after the advent of LLMs.

We could have mods for old games that generate voices for the characters for example. Maybe it's unfeasible from a computing perspective? There are people running local LLMs, no?

Re: Diffusion models are real-time game engines

#53

There is no text conditioning provided to the SD model because they removed it, but one can imagine a near future where text prompts are enough to create a fun new game! Yes they had to use RL to learn what DOOM looks like and how it works, but this doesn’t necessarily pose a chicken vs egg problem. In the same way that LLMs can write a novel story, despite only being trained on existing text. IMO one of the biggest…

> where text prompts are enough to create a fun new game!

Not really. This is a reproduction of the first level of Doom. Nothing original is being created.

Re: Diffusion models are real-time game engines

#54
post #26

Earlier quoted context omitted.

It confused me that their stated evaluations by humans are comparing video clips rather than evaluating game play.

Short clips are the only way a human will make any errors determining which is which.

More relevant is if by _playing_ it they couldn’t tell which is which.

Re: Diffusion models are real-time game engines

#55
What most programmers don't understand, that in the very near future, the entire application will be delivered by an AI model, no source, no text, just connect to the app over RDP. The whole app will be created by example, the app developer will train the app like a dog trainer trains a dog.

Re: Diffusion models are real-time game engines

#56
post #45

Earlier quoted context omitted.

Image is 2D. Video is 3D. The mathematical extension is obvious. In this case, low resolution 2D (pixels), and the third dimension is just frame rate (discrete steps). So rather simple.

This is not "just" video, however. It's interactive in real time. Sure, you can say that playing is simply video with some extra parameters thrown in to encode player input, but still.

It is just video. There are no external interactions.

Heck, it is far simpler than video, because the point of view and frame is fixed.

Re: Diffusion models are real-time game engines

#57
post #4

So, diffusion models are game engines as long as you already built the game? You need the game to train the model. Chicken. Egg?

Maybe, in future, techniques of Scientific Machine Learning which can encode physics and other known laws into a model would form a base model. And then other models on top could just fine tune aspects to customise a game.

Re: Diffusion models are real-time game engines

#58

There's been a ton of work to generate assets for games using AI: 3d models, textures, code, etc. None of that may even be necessary with a generative game engine like this! If you could scale this up, train on all games in existence, etc. I bet some interesting things would happen

But can you grab what this Ai has learned and generate the 3d models, maps and code to turn it into an actual game that can run on a user's PC? That would be amazing.

Jensen Huang's vision that future games will be generated rather than rendered is coming true.

Re: Diffusion models are real-time game engines

#59
post #3

The quest to run doom on everything continues. Technically speaking, isn't this the greatest possible anti-Doom, the Doom with the highest possible hardware requirement? I just find it funny that on a linear scale of hardware specification, Doom now finds itself on both ends.

> Technically speaking, isn't this the greatest possible anti-Doom, the Doom with the highest possible hardware requirement? Not really? The greatest anti-Doom would be an infinite nest of these types of models predicting models predicting Doom at the very end of the chain. The next step of anti-Doom would be a model generating the model, generating the Doom output.

Isn't this technically a model (training step) generating a model (a neural network) generating Doom output?
Post reply on HN