Being young today must be fun. Just missed out on all the good stuff in the 80, 90s and 2000s to experience this mess we have now.

Unforunately the latest stuff I've seen is all about keeping character consistency, which is basically having a fixed frame of reference for every generation. What I don't get not knowing much about the details is how LLM generation is faster than actual 3D modeling with more details? Perhaps overall it is faster per frame to generate a 2D image vs. tracking all the polys.

Not saying which is right to do, there's lots of baggage with discussing AI stuff, just wondering about the actual tech itself.

Double Latency Slow Sloppification.

All of this upscaling when it was presented over a decade ago was to give older cards a longer lease in life and now it's morphed into the mandatory way to get a stable framerate since developers can now just rely on DLSS and to a lesser extent FSR to get them to a acceptable framerate instead of optimization.

As for how will this improve the gaming experience? I honestly don't see it at this point. Back when it was the original goal, sure, now with this "Chat GPT moment for graphics", I see it only beneficial for corporate parasites and "shareholder value" as we wave good bye to artistic vision as everything goes to looking like AI only fans.

It makes "I fixed this ugly FEMALE character" chuds happy and that's what matters to them.

Saves payroll on artists which means more profits. #winning

I think the idea is that you could use low resolution / detail models that take up less RAM and are faster to process and DLSS hallucinates a high res image.

Not a fan of reimagined stuff of any sort, it usually doesn't hit well. But from a tech standpoint I can think of ways one could use the tech to improve game performance for new games. Usually making a game run faster or feel more realistic is all about fooling the player, not drawing what's not seeable, showing hints of things that aren't really there. Hell, that's been true for movies and even stage, right?

So my thought on how this could work is to have the actual core models be lower polys, enough for details but not as high as the best we've seen done, and minimal texturing. Then the generator uses that as a base to form the image it puts over the top. Still don't see how that can be done that fast, but apparently we're there now.

Nvidia realized they hit a wall on rendering... So they went full on into something that you can't properly benchmark - especially against competitors AND prior generations.

Nvidia went full snake oil... And really would like people not to notice.

I guess by this description that perhaps it would be good for something like resident evil that strives to give you that uncanny creepiness no?

That would only work i they still gave a shit about gamers or the consumer market in general. They became a full AI Datacenter company, thats where they make the money. I don't think they will even produce consumer graphics cards in 5 years anymore.

I don't think developers and artists have a choice when they're being told by the publishers to do it.

The problem is that these 'features' give you the fake appearance of performance but at the cost of actual performance. And they aren't even good in the first place. Upscaling is like smearing vaseline all over your screen and saying "see how good it looks" when it's just a blurry mess, especially with temporal elements. Frame generation gives artificial smoothness but doesn't help input latency which is the part of frame rate that actually matters.

The kicker is that it costs real frames to generate fake ones. The game ends up looking and feeling worse.

I dislike upscaling, it always looks off to me and frequently causes edges of things to be weird kind of like aliasong but different. After upgrading from a gtx 3060, where I only used it for a few games that were hectic enough to not notice it as much, to a 9070xt I turned off upscaling globally and run everything in the native resolution. Games look so much better without dlss or fsr to me, fewer weird artifacts causing distractions.

I'll take 20 less fps to not constsntly feel like something is off even if I can't point out exactly what it is.

The magic here is you always have the option in most game settings, to turn it off.

It can't, remastering games is an entirely different process that requires artistic direction. Piping a game's video output through an AI filter just takes the original game and smears a bunch of slop over it.