Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Rendering a game in real time with AI

blog.jeffschomay.com

Post reply on HN
Print view View original

31–40 of 115 posts

Re: Rendering a game in real time with AI

#31

Post by ozmodiar »

sjsdaiuasgdia wrote: post #2

The "real-time" version looks awful with constantly shifting colors, inconsistently sized objects, and changing interpretations of the underlying data, resulting in what I would consider an unplayable game vs the original ASCII rendering. The "better" version renders at a whopping 4 seconds per frame (not frames per second) and still doesn't consistently represent the underlying data, with shifting interpretations of…

I like the idea behind https://oasis-ai.org/ where you can actually try to take advantage of the 'dream logic' inconsistency of each frame being procedurally generated based on the last one. For example, instead of building a house, build the corner of a house, look at that, then look back up and check if it hallucinated the rest of your ephemeral house for you. Of course that uses AI as the entire gameplay loop and not just a graphics filter. It's also... not great, but an interesting concept that I could see producing a fun dream logic game in the future.

Re: Rendering a game in real time with AI

#32

Post by lukan »

abbycurtis33 wrote: post #28
coolKid721 wrote: post #23

I do not get the point of this at all, why not just generate game assets and run them in an engine? With this format there would be no regularity that the thing you saw before will look the same (and that is not a fixable problem). Actually figuring out and improving AI approaches for generating consistent and decent quality game assets is actually something that will be useful, this I have no idea the point of past…

The tech will improve to far exceed the capabilities of a game engine. Real time improvisation and infinite choices, scope, etc. It makes no sense when people say AI can't do this or that. It will do it next week.

"It makes no sense when people say AI can't do this or that. It will do it next week."

So full self driving vecicles will be finally ready next week then? Great to hear, though to be honest, I remain sceptical.

Re: Rendering a game in real time with AI

#34

Post by mason_mpls »

tantalor wrote: post #25
cbm-vic-20 wrote: post #10

...where "ASCII" means an image made up of a grid of elements from a limited set of glyphs.

And those glyphs are not ASCII This is ASCII: https://commons.wikimedia.org/wiki/File:ASCII-Table-wide.svg

If we’re talking about dwarf fortress it uses an old IBM charset, assuming this is some branch off that

Re: Rendering a game in real time with AI

#35

Post by kayamon »

lukan wrote: post #32
abbycurtis33 wrote: post #28

Earlier quoted context omitted.

The tech will improve to far exceed the capabilities of a game engine. Real time improvisation and infinite choices, scope, etc. It makes no sense when people say AI can't do this or that. It will do it next week.

"It makes no sense when people say AI can't do this or that. It will do it next week." So full self driving vecicles will be finally ready next week then? Great to hear, though to be honest, I remain sceptical.

Waymos are driving themselves around several cities right now.

Re: Rendering a game in real time with AI

#37

Post by sho_hn »

coolKid721 wrote: post #23

I do not get the point of this at all, why not just generate game assets and run them in an engine? With this format there would be no regularity that the thing you saw before will look the same (and that is not a fixable problem). Actually figuring out and improving AI approaches for generating consistent and decent quality game assets is actually something that will be useful, this I have no idea the point of past…

> I do not get the point of this at all

Dunno, this seems like an avenue definitely worth exploring.

Plenty of game applications today already have a render path of input -> pass through AI model -> final image. That's what the AI-based scaling and frame interpolation features like DLSS and FSR are.

In those cases, you have a very high-fidelity input doing most of the heavy lifting, and the AI pass filling in gaps.

Experiments like the OP's are about moving that boundary and "prompting" with a lower-fidelity input and having the model do more.

Depending on how well you can tune and steer the model, and where you place the boundary line, this might well be a compelling and efficient compute path for some applications, especially as HW acceleration for model workloads improves.

No doubt we will see games do variations of this theme, just like games have thoroughly explored other technology to generate assets from lower-fidelity seeds, e.g. classical proc gen. This is all super in the wheelhouse of game development.

Some kind of AI-first demoscene would be a pretty cool thing too. What's a trained model if not another fancy compressor?

Re: Rendering a game in real time with AI

#39

Post by turnsout »

coolKid721 wrote: post #23

I do not get the point of this at all, why not just generate game assets and run them in an engine? With this format there would be no regularity that the thing you saw before will look the same (and that is not a fixable problem). Actually figuring out and improving AI approaches for generating consistent and decent quality game assets is actually something that will be useful, this I have no idea the point of past…

It's an interesting tech demo—I think one interesting use case for AI rendering is changing the style on the fly. For example, a certain power-up could change the look to a hyper-saturated comic book style. Definitely achievable with traditional methods, but because AI is prompt-based, you could combine or extend styles dynamically.

Re: Rendering a game in real time with AI

#40

Post by 127 »

coolKid721 wrote: post #23

I do not get the point of this at all, why not just generate game assets and run them in an engine? With this format there would be no regularity that the thing you saw before will look the same (and that is not a fixable problem). Actually figuring out and improving AI approaches for generating consistent and decent quality game assets is actually something that will be useful, this I have no idea the point of past…

Visually speaking, there's always visual issues in tying disparate assets together in a seamless fashion. I can see how AI could be easily used to "hide the seams" so to speak. I think a hybrid approach would be an improvement definitely.
Post reply on HN