• Hey Guest. Check out your NeoGAF Wrapped 2025 results here!

Graphical Fidelity I Expect This Gen

wywktsepam9e1.gif


Every argument I've seen against it is purely emotional, none of them are technical.
People complained about ray tracing when it first came out. Today it's the industry standard and nobody complains anymore (maybe console gamers and AMD GPU users).
It s hillarious that amd console owners think they will get this tech anyway.
If you only play consoles you will never get this tech for at least a decade or more.
 
Last edited:
And about "artistic intent", isn't this also messing with the "artistic intent?" Because this looks far away from the original intended art.

K66vOPAmk3GzGl7P.jpeg

Nah, this is just bad graphics done by developers who clearly dont give a shit about character models looking good during gameplay. You can easily fix this with hero lighting. We dont need an AI pass to fix stuff like this.

This is what Grace's model looks like in model viewer. It looks nothing like what the Nvidia AI model's interpretation. Or rather hallucination.

v5APXf3zC0JElx4r.jpg
 
That, but also I think the issue is that virtual humans are just not cut out for attempts at photorealism. As we're edging closer to that, it's creating this uncanny valley effect that audiences aren't comfortable with. DLSS5 could be as far away from slop as it could be, and I imagine a lot of people would still be repulsed.

I think chasing photorealism is fine in game environments as our minds are not trained to spot when a shadow doesn't cast just the right way. That's why rasterization tricks have gotten us so far. But our minds are trained (probably through evolution) to spot and warn when a person or creature doesn't look right.

I think this is why Rockstar are still leaning into their characters looking just stylized and 'videogame-y' enough so that they step past the uncanny valley.

fMXHFEkPNh7IO9Sm.jpg
nah we already have plenty of games that do photorealistic graphics with real life actors. Our brains dont reject them because they are done well. Starfield and Zora AI humans look wrong for the same reason day time Soap Opera looks off. No one wants to play real life.

See below:

I think nvidia engineers have kinda misread the market here. This is currently happening at every major tech firm so im not surprised that the execs and engineers at nvidia are also in their own little bubble.

Here is the thing, gamers largely praised games that went with a photorealistic art styles and character models. Hellblade 2, Matrix and Marvel 1943 were roundly praised by the same people showing an absolute disdain over this. I still think it's largely due to the AI faces completely missing the original lighting pass resembling Sora AI videos than the original game. But it's still a valid concern that apparently nvidia engineers and marketing guys were completely oblivious to.

The examples below showcase that people are enamored with photorealism in video games. This is possible on a 10 tflops card. We are going to 30-40 tflops cards next year. We can easily get to photorealism organically without taking any shortcuts. I think Nvidia just didnt realize that we had to get there ourselves.

rBWdEWZ.gif
8ba82e817e6ee5d2b9658a3b624a20137fcd3c68.gifv



b570ccd329c084906dd82b0654db042ba5491a3a.gifv
HDko0qpaIAA8Cbn
 
Nah, this is just bad graphics done by developers who clearly dont give a shit about character models looking good during gameplay. You can easily fix this with hero lighting. We dont need an AI pass to fix stuff like this.

This is what Grace's model looks like in model viewer. It looks nothing like what the Nvidia AI model's interpretation. Or rather hallucination.

v5APXf3zC0JElx4r.jpg
You didn't address my point but I understand what you mean. I think it is important to dissect what people mean by graphics & art, they're already struggling to separate games with photorealistic art VS what they deem as "art", which is any game that doesn't emulate real-life.

You say Raster mode is bad graphics, many people say it's artistic intent.

I am also not saying we NEED DLSS 5 to improve graphics, the PT mode is already phenomenal as is, the DLSS 5 needs manual correction, Grace here looks too realistic & Instagram-y for the game's rather gamey visuals in comparison, at the same time, I will say Grace looks like a cardboard box in Ratser mode, she looks like a drug addict who had a severe case of Urinary Tract Infection.
 
Last edited:
You didn't address my point but I understand what you mean. I think it is important to dissect what people mean by graphics & art, they're already struggling to separate games with photorealistic art VS what they deem as "art", which is any game that doesn't emulate real-life.

You say Raster mode is bad graphics, many people say it's artistic intent.

I am also not saying we NEED DLSS 5 to improve graphics, the PT mode is already phenomenal as is, the DLSS 5 needs manual correction, Grace here looks too realistic & Instagram-y for the game's rather gamey visuals in comparison, at the same time, I will say Grace looks like a cardboard box in Ratser mode, she looks like a drug addict who had a severe case of Urinary Tract Infection.
I thought I did address your point. You said that they dont have control over Grace looking like that in the raster version. They do. They just chose not to. They arent the only ones, we have talked about it ad nauseum in this thread. TLOU1 Remake discussion in this very thread pretty much revolved around the characters looking like dogshit during gameplay.

I think you and I agree that the character models need to look more gamey/cg rather than photorealistic because this is completely different from what the artist imagined when they created the character model. But i just disagree that they dont have control over it especially since we have examples like Hellblade 2, Callisto and best of all HFW.
 
No the clear solution is to do the same thing they have been doing.

When you go to turn on rt they give you options that include rt shadows, rt ao, rtgi as seperate boxes. They will do the same with this tech. Boxes to check whether or not to include the faces and sliders fo dial in the effect. Options.
why-not-both.gif
 
Nah, this is just bad graphics done by developers who clearly dont give a shit about character models looking good during gameplay. You can easily fix this with hero lighting. We dont need an AI pass to fix stuff like this.

This is what Grace's model looks like in model viewer. It looks nothing like what the Nvidia AI model's interpretation. Or rather hallucination.

v5APXf3zC0JElx4r.jpg
She still looks a porcellain doll compared to the best a ps4 can offer

DWx9Des6jwQQr6uAJBsXu8.jpg


You genuinely can't think that grace represent a realistic woman face in her current version.
 
Last edited:
She still looks a porcellain doll compared to the best a ps4 can offer

DWx9Des6jwQQr6uAJBsXu8.jpg


You genuinely can't think that grace represent a realistic woman face in her current version.
ive always said that her character model in the game looks last gen. hell, she looks last gen compared to Leon.

But what nvidia is doing is completely making her up. its not been fed the face of the real actress. its not been fed anything other than real life pictures of pornstars and models.

Jensen just gave an interview saying that devs have full control. And i say nonsense. They dont have control over the model. If they did, Grace's AI model would not look completely different. Or maybe they do and Capcom engineers are just trolling nvidia by making it look worse.

"The reason for that is because, as I have explained very carefully, DLSS 5 fuses controllability of the of geometry and textures and everything about the game with generative AI," Huang continued.

He added that developers can still "fine-tune the generative AI" to make it match their style, adding that DLSS 5 adds generative capability to the existing geometry of the game, but that it "doesn't change the artistic control."

"It's not post-processing, it's not post-processing at the frame level, it's generative control at the geometry level," he said.

Huang also said that developers can try the tool and see how they want to use it, suggesting that it's up to a developer to try to make a "toon shader" or see if the game should be "made of glass."

"All of that is in the control — direct control — of the game developer," he said. This is very different than generative AI; it's content-control generative AI. That's why we call it neural rendering."

I love the tech. I think its mind blowing, but they need to train it on a game by game basis. Or maybe movies. Right now, its just making shit up and the character models especially look completely off. I actually think the worlds look great and i would love to try it out.
 
Last edited:
ive always said that her character model in the game looks last gen. hell, she looks last gen compared to Leon.

But what nvidia is doing is completely making her up. its not been fed the face of the real actress. its not been fed anything other than real life pictures of pornstars and models.

Jensen just gave an interview saying that devs have full control. And i say nonsense. They dont have control over the model. If they did, Grace's AI model would not look completely different. Or maybe they do and Capcom engineers are just trolling nvidia by making it look worse.









I love the tech. I think its mind blowing, but they need to train it on a game by game basis. Or maybe movies. Right now, its just making shit up and the character models especially look completely off. I actually think the worlds look great and i would love to try it out.
You sincerely think devs don't have control? cmon man let's not go nuts with the conspiracy.

Always remember that gaf is a bubble, tiktok filters are famous because a large part of the planet like that stuff and the pendulum is swinging so devs are trying to over-correct the ugliness of the past 5-6 years, with sometimes dubious results, i give you that.

( i still think dlss5 grace look 10x times more of a real woman than the current model tho)
 
Last edited:
That, but also I think the issue is that virtual humans are just not cut out for attempts at photorealism. As we're edging closer to that, it's creating this uncanny valley effect that audiences aren't comfortable with. DLSS5 could be as far away from slop as it could be, and I imagine a lot of people would still be repulsed.

I think chasing photorealism is fine in game environments as our minds are not trained to spot when a shadow doesn't cast just the right way. That's why rasterization tricks have gotten us so far. But our minds are trained (probably through evolution) to spot and warn when a person or creature doesn't look right.

I think this is why Rockstar are still leaning into their characters looking just stylized and 'videogame-y' enough so that they step past the uncanny valley.

fMXHFEkPNh7IO9Sm.jpg
Hellblade 2 has some almost completely photorealistic moments.
 
Have you people completely lost it?
Do you think grace looks as good or better than these? It doesn't even look close. it looks 10x worse.
Its almost like everyone in this thread has had collective amnesia.

There are no free lunches, either you spend the 2nd 5090 equivalent power rendering the path tracing 2.0 environment below or you spend it on your beloved AI slop filter.

You can't have it both ways. People say, well its optional you can just turn it off. These people need to turn on their brains.
Its NOT optional. When DLSS was added it took up a significant portion of the die space that would have gone to traditional gpu pipeline.
Now it was worth while and a worthy cause from Day 1. But just turning it off didnt remove the tensor cores from your gpu and give you those removed gpu. The same way the 2nd 5090 equivalent tensor cores have now been reserved for this AI Slop.

So rather than spending the power of that tensor cores for the below. it will be spent on AI slop.
So turning it off just means ALL THAT die space on your GPU become useless because they have been reserved for AI slop.

bmI6m.png


widen_1840x0.jpeg



6960c4130f4e8.gif


giphy.gif


d4a89f7e9403218b79d67bde24287c57522abbf8.gif




dd61ff146438613.62b17c22bd338.jpg


18884e146438613.62b17c22c0a61.jpg


14ffd7146438613.62b17c22bb26e.jpg
This is the future.
 
You sincerely think devs don't have control? cmon man let's not go nuts with the conspiracy.

Always remember that gaf is a bubble, tiktok filters are famous because a large part of the planet like that stuff and the pendulum is swinging so devs are trying to over-correct the ugliness of the past 5-6 years, with sometimes dubious results, i give you that.

( i still think dlss5 grace look 10x times more of a real woman than the current model tho)
They dont have control over the actual model. They have control over the intensity sliders which will allow devs to reduce the photorealism of the character models. We will see if devs can make it look non AI sloppy. But so far the results in virtually every game by every developer look very slop-ish.
 
You sincerely think devs don't have control? cmon man let's not go nuts with the conspiracy.
It´s a model reimagining pictures plus some buffer values. It´s not exactly a straightforward process to finetune these models in any way. Maybe Devs get the possibility to do specific trainingssets based on what they want to see, but that would contradict the "general model" principle, who knows.

Always remember that gaf is a bubble, tiktok filters are famous because a large part of the planet like that stuff
Adding a dog-snout and bunny ears to a person for a 30 second clip is so far away from looking at a "this probably looks like this"-AI video you`re interacting with for hours that I simply can`t express how nonsensical that comparison is.

( i still think dlss5 grace look 10x times more of a real woman than the current model tho)
The point itsn´t that she looks more realistic, if you think of that AI-slop fotostudio-look in that way, but that the AI completely changed the model while some retards are still claiming "it`s just the lighting". This isn`t enhancement based on the actual ground truth, it`s reimagination, that`s the point and the issue a lot of people have with this.
 
Last edited:
If you run Nvidia and you don't want people to walk away from a presentation with this take, then you and (the developers that worked with you) have to show better examples to begin with.

Or just be slightly more aware of the public's feelings on generative AI so that you can show something that gives off a better feeling when looking at it.

The same public that's already eating up generative AI in their daily life and previous DLSS applications? The same hypocrites?

My hope is that the tech runs fine at 1440p on 5080 and can run on older games. Could see myself replaying Black Desert with this as the game's lighting is all kinds of messed up.
No appetite for Starfield on PS5 with the old gen faces. This could give a second life to some older games.
 
Last edited:
It´s a model reimagining pictures plus some buffer values. It´s not exactly a straightforward process to finetune these models in any way. Maybe Devs get the possibility to do specific trainingssets based on what they want to see, but that would contradict the "general model" principle, who knows.


Adding a dog-snout and bunny ears to a person for a 30 second clip is so far away from looking at a "this probably looks like this"-AI video you`re interacting with for hours that I simply can`t express how nonsensical that comparison is.


The point itsn´t that she looks more realistic, if you think of that AI-slop fotostudio-look in that way, but that the AI completely changed the model while some retards are still claiming "it`s just the lighting". This isn`t enhancement based on the actual ground truth, it`s reimagination, that`s the point and the issue a lot of people have with this.
I was not talking about that type of filter, obviously.

For the rest, no offense guys, but you know jack shit about how much an artist can change the result.

Before being catastrophic, maybe let's wait to see how the tech evolve.

I do agree that the change is clearly more than lighting, i thought that was clear for everyone.

SlimySnake SlimySnake dude this was literally your first reaction to dlss5

DLSS 5 is incredible. A fucking photorealistic filter. WTF is even happening.

is this a joke? Im watching the DF video. please dont play with my heart like this. it is fucking insane.


and this was your second post where you were posting the grace example

WHAT. THE. FUCK.


You were impressed as much as many of us so don't come at me with this very slop-ish revisionism :lollipop_grinning_sweat:

If i admit that some of them are weird you must admit that a lot of them are incredible and the potential is bottomless if the tech is properly developed ad used.
 
Last edited:
For the rest, no offense guys, but you know jack shit about how much an artist can change the result.

Before being catastrophic, maybe let's wait to see how the tech evolve.
the main issue, the very nature of this tech, will not change:
"This isn`t enhancement based on the actual ground truth, it`s reimagination"



on to more uplifitng things.
Guys, remember Death Stranding 2`s release when the press was singing praises to Decima, calling it the UE killer, asking why anybody would want RT?
Well, the PC release is imminent and official screenshots like this one remind me that the mainstream really doesn´t know jack shit about graphics.
55145306286_b9aa36f926_k.jpg



I wonder if people would still say the same now that RE9 has gotten mainstream attention with PT Screenshots floating around everywhere.
 
Last edited:
The same public that's already eating up generative AI in their daily life and previous DLSS applications? The same hypocrites?
Different audiences.

Same reason why Marvel video games are selling just fine yet the movies and TV are in a downward slump (aside from just Deadpool).

I bring this up all the time when people here want to falsely proclaim that superhero fatigue is an all-around thing.
 
the main issue, the very nature of this tech, will not change:
"This isn`t enhancement based on the actual ground truth, it`s reimagination"
At worse we can decide to not use it or use like a low setting.

If the backlash is big maybe devs\nvidia are gonna take note and adjust things accordingly.

I still think you people are being way too pessimistic and i'm usually the pessimistic one in here.
 
At worse we can decide to not use it or use like a low setting.
I wouldn´t be so sure about that. If this finds broad acceptance and AMD comes around with their own solution we might very well see a massive regression in the actual game graphics in favor of "optimized to be filled in by AI" simply for cost reasons. If the models get stable and cheap (performance wise) enough for this kind of job description we will get this stuff forced down our throats because money always wins in the end.
Being able to skip large parts of the very...very.... expensive asset creation process would definitely be something that gives every Gaming CEO a boner.
Well, the next console gen will probably never run anthying like this, so we got another 6-7 years until that question might become pressing.
 
Last edited:
I wouldn´t be so sure about that. If this finds broad acceptance and AMD comes around with their own solution we might very well see a massive regression in the actual game graphics in favor of "optimized to be filled in by AI" simply for cost reasons. If the models get stable and cheap (performance wise) enough for this kind of job description we will get this stuff forced down our throats, because money always wins.
Being able to skip large parts of the very...very.... expensive asset creation process is definitely something that gives every Gaming CEO a boner.
Ok but now you are talking in a more broader term, not just nvidia.

We can only hope they don't go overboard.
 
SlimySnake SlimySnake dude this was literally your first reaction to dlss5

DLSS 5 is incredible. A fucking photorealistic filter. WTF is even happening.

is this a joke? Im watching the DF video. please dont play with my heart like this. it is fucking insane.


and this was your second post where you were posting the grace example

WHAT. THE. FUCK.


You were impressed as much as many of us so don't come at me with this very slop-ish revisionism :lollipop_grinning_sweat:

If i admit that some of them are weird you must admit that a lot of them are incredible and the potential is bottomless if the tech is properly developed ad used.
Think about how many people buy a hyped game or watch a hyped movie and then take a second and third look at it.

It's literally why I called it a while back that Deadpool and Wolverine might age badly as a movie, even though it was admittedly a fun first watch theater experience.
 
SlimySnake SlimySnake dude this was literally your first reaction to dlss5

DLSS 5 is incredible. A fucking photorealistic filter. WTF is even happening.

is this a joke? Im watching the DF video. please dont play with my heart like this. it is fucking insane.


and this was your second post where you were posting the grace example

WHAT. THE. FUCK.


You were impressed as much as many of us so don't come at me with this very slop-ish revisionism :lollipop_grinning_sweat:

If i admit that some of them are weird you must admit that a lot of them are incredible and the potential is bottomless if the tech is properly developed ad used.
And i said this to you five minutes ago:
I love the tech. I think its mind blowing,
I actually think the worlds look great and i would love to try it out.
I dont know what more i can say at this point.
 
Last edited:
PSSR2 is the real deal. Finally upto par with DLSS. Looks really good in FF7 Rebirth. A lot of detail finally resolving. Spiderman 2 looks really clean as well. No dithering and shimmering in the distance. TLOU2 looks stunning. I switched between 4k and PSSR and they look virtually identical. Some small issues resolving fences and foliage, but very minor.

Ended up watching cutscenes in native 4k for like half an hour. Amazing acting and facial animations. The game looks incredible in 4k. Not seeing anything from ND this gen is the worst fucking timeline.
 
Different audiences.

Same reason why Marvel video games are selling just fine yet the movies and TV are in a downward slump (aside from just Deadpool).

I bring this up all the time when people here want to falsely proclaim that superhero fatigue is an all-around thing.

I just think people should just have a more measured take on this, instead of screaming AI slop while already reaping the benefits of said AI.
You even had posters here going full meltdown mode saying game art will disappear because of DLSS... Honestly all this is could be linked to so many Youtubers feeding off the hate/ memes, etc..

Like I said I'm excited for this tech cause could be used to give older games new life, let's see where this goes.

 
I just think people should just have a more measured take on this, instead of screaming AI slop while already reaping the benefits of said AI.
You even had posters here going full meltdown mode saying game art will disappear because of DLSS... Honestly all this is could be linked to so many Youtubers feeding off the hate/ memes, etc..

Like I said I'm excited for this tech cause could be used to give older games new life, let's see where this goes.


I agree with the measured take, but not on the positive side of things, and that means a lot from me since I don't usually like how negative this forum can be on a lot of things. However, this specifically should be treated with a high level of skepticism until proven otherwise.

This guy did research and explains it all really well at 4:04



And he came away from it all just as worried.
 
I agree with the measured take, but not on the positive side of things, and that means a lot from me since I don't usually like how negative this forum can be on a lot of things. However, this specifically should be treated with a high level of skepticism until proven otherwise.

This guy did research and explains it all really well at 4:04



And he came away from it all just as worried.


Right away his beef is that the focus on Jensen conference is not on this tech alone? And after he says we all agree the faces look terrible? Yeah sorry but nah.

"I've analysed this tech that I can't put my hands on and all I have to run with his this article, and a couple of videos, so here's my take on it = AI slop"

Clickbait thumbnails also tells me all I need to know about the video.
 
Last edited:
Right away his beef is that the focus on Jensen conference is not on this tech alone? And after he says we all agree the faces look terrible? Yeah sorry but nah.

"I've analysed this tech that I can't put my hands on and all I have to run with his this article, and a couple of videos, so here's my take on it = AI slop"

Clickbait thumbnails also tells me all I need to know about the video.
Watch the whole video instead of skimming through it or closing it once you disagree with a single point. If I can watch your video all the way through, the least you could do is return the favor.

Edit: And I can tell you haven't watched it because he gives it some complimentary points later on, but also states his worries.
 
Last edited:
Right away his beef is that the focus on Jensen conference is not on this tech alone? And after he says we all agree the faces look terrible? Yeah sorry but nah.

"I've analysed this tech that I can't put my hands on and all I have to run with his this article, and a couple of videos, so here's my take on it = AI slop"

Clickbait thumbnails also tells me all I need to know about the video.
You right now
Not Listening Rachael Ray GIF by ABC Network
 
Last edited:
I thought I did address your point. You said that they dont have control over Grace looking like that in the raster version. They do. They just chose not to. They arent the only ones, we have talked about it ad nauseum in this thread. TLOU1 Remake discussion in this very thread pretty much revolved around the characters looking like dogshit during gameplay.

I think you and I agree that the character models need to look more gamey/cg rather than photorealistic because this is completely different from what the artist imagined when they created the character model. But i just disagree that they dont have control over it especially since we have examples like Hellblade 2, Callisto and best of all HFW.
I know they can have greater control over how Grace looks in Raster mode than what's in the final product, but this is the final product, and Grace looks rather ugly in most cases, so I will judge what I see, and all I see is the uglification of the Artist's truest intents.

In my 1st reply to you, I was speaking about the nature of calculable real-time solutions, like shadow maps, you can't control those, they just cast shadows from point lights, the hardware is calculating all that. it's not like pre-baking maps where every pixel the developer has "control" over.

The people that protest "ART ART ART" typically miss the degrees of how much developers have control over any rendering solution, they think even the graphical weaknesses/limitations are part of the "charm" or "art" because the artist built around them, whenever there is a new solution that needs next-generation hardware, studios will use those features, and now it's DLSS 5, which for sure will get them closest to their art.

I can conclude that the usage of Neural Rendering from what we've seen now in RE9 represents a mishandling of the technology, will it get better? Of course it would, will developers & artists be more careful with it? Yes. There are already a huge influx of game studios & developers believing in DLSS 5 & Neural Rendering in general, it has been reported by a Journalist that was present at this year's GDC.
 
You right now
Not Listening Rachael Ray GIF by ABC Network

Well there are about dozens of videos repeating the same thing...Facts stay the same: need more footage, the tech needs to be tested and I personally like the lighting improvements.

Watch the whole video instead of skimming through it or closing it once you disagree with a single point. If I can watch your video all the way through, the least you could do is return the favor.

Edit: And I can tell you haven't watched it because he gives it some complimentary points later on, but also states his worries.

Fair enough.
 
Last edited:
Well there are about dozens of videos repeating the same thing...Facts stay the same: need more footage, the tech needs to be tested and I personally like the lighting improvements.
Fact is that you haven't watched the video. No need to even listen to the YouTuber at all as he did a good job just putting the problematic material together showing the issues, which are the same as in all AI videos, and highlighting the official info from Nvidia regarding the type of tech we're looking at here ... Suprise suprise it's an AI filter with motion vectors for stabilization. Slop.
We know what this tech does it's not exactly a secret. And the lighting, just as everything else is not improved.. It's reimagined. The light sources that you see in the slop version of many scenes shouldn't even exist ...
 
Last edited:
Ok but now you are talking in a more broader term, not just nvidia.

We can only hope they don't go overboard.
Neural Rendering is betted on by Sony, Microsoft, AMD, Intel and everybody in the scene, people should just accept that this is the future of real-time rendering, you got the top Engineers in the world in each of these companies telling you it's that.

Not saying you shouldn't be skeptic towards DLSS 5, be skeptic, some of the demos they've shown looked funky, but please know that it'll get much better as we go along.
 
Last edited:
Fact is that you haven't watched the video. No need to even listen to the YouTuber at all as he did a good job just putting the problematic material together showing the issues, which are the same as in all AI videos, and highlighting the official info from Nvidia regarding the type of tech we're looking at here ... Suprise suprise it's an AI filter with motion vectors for stabilization. Slop.
We know what this tech does it's not exactly a secret. And the lighting, just as everything else is not improved.. It's reimagined. The light sources that you see in the slop version of many scenes shouldn't even exist ...

I just finished watching it.
I can agree it needs work, probably why we don't have lengthy footage of it, but it's not out yet and in no one's hands so he's opinion's still only based off the footage they have released which he doesn't like... cool. I do, and see pontential in it, that's pretty much it?
 
Top Bottom