• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

DLSS 5.0

leSLIe

leSLIe

Fully [H]
Joined
Oct 18, 2004
Messages
17,346
HDjXeKvbwAAE9Us.jpeg


HDjXeozW4AEW1Jl.jpeg


DLSS 5 aka AI snapchat filter. 😏
 
For the first time, I'm kind of not feeling great about a new DLSS version 😕 the improvements to environments look great but on the character models I'm more ehh.
 
  • Like
Reactions: erek
like this
looks like the big improvement with DLSS 5.0 is the lighting...I like it but I want to see some actual independent reviews (Hardware Unboxed, Digital Foundry) and not Nvidia's own marketing hype...will Nvidia make it exclusive to the 5000 series and above due to some artificial hardware limitation?
 
I'm not sure why people are clowing on it so much, it makes the lighting look much more realistic for sure. Maybe they can argue artists intent, but it's pretty clear in most of the examples shown that the artists are striving for realism to some degree at least.

The big fail IMO is bundling this tech and everything else under "DLSS", because this lighting enhancment seems to be completely seperate from the upscaling/super sampling side of DLSS, and they're saying it will be a seperate option to enable in games like frame generation as well. They should just call it something else like RTX lighting or something.

It seems to be pretty early in development too if they need an entirely seperate 5090 just to enable the effect on the game. I'm sure they're working to optimize and scale it down for slower GPUs, as it wouldn't be very enticing to use on 5090 level performance cards for the next generation or two. But I suppose that's pretty much how RT worked for its first generation or two when Turing debuted it. It just doesn't seem like it should really be that expensive of an effect to apply (compared to ray/path tracing) once the ML model has thuroughly learned it and makes it available in the drivers.
 
T4rd said:
I'm not sure why people are clowing on it so much, it makes the lighting look much more realistic for sure. Maybe they can argue artists intent, but it's pretty clear in most of the examples shown that the artists are striving for realism to some degree at least.

The big fail IMO is bundling this tech and everything else under "DLSS", because this lighting enhancment seems to be completely seperate from the upscaling/super sampling side of DLSS, and they're saying it will be a seperate option to enable in games like frame generation as well. They should just call it something else like RTX lighting or something.

It seems to be pretty early in development too if they need an entirely seperate 5090 just to enable the effect on the game. I'm sure they're working to optimize and scale it down for slower GPUs, as it wouldn't be very enticing to use on 5090 level performance cards for the next generation or two. But I suppose that's pretty much how RT worked for its first generation or two when Turing debuted it. It just doesn't seem like it should really be that expensive of an effect to apply (compared to ray/path tracing) once the ML model has thuroughly learned it and makes it available in the drivers.
Click to expand...
Yeah they shouldve called it something different.
They also said the developers will be able to tweak the looks. But in Starfield the faces have a complete make over
 
I see potential, but also see it as enabling ENB in every game without the option to adjust it for preference. It will game games look more similar. They should offer some user control, not just developer control.
 
Luckily you have the option to not use it. But this whole fake frame thing is getting out of control. Now the instead of the developers deciding how the game should look the graphics card company decides what I get to see. Feels like Nvidia is just grabbing more and more control of what developers can do.
 
kram182 said:
Mods and mod sites need to be banned because they ruin the creator's artistic intent 😤
Click to expand...
What the "A.I slop" crowd fail to realise is that Capcom, Bethesda, EA and Avalanche developers had a hand in what was presented.

This is just "faux" rage, because A.I. hurt the pricing for people.
They cannot stop it, so they whine like a 2 year old child.
 
leSLIe said:
the return of SLI ?
Click to expand...
I saw that too. It takes two 5090's to run this thing. Good grief.

I don't get all the hate though. This is pretty great.

As far as the claim, all games will look the same, well duh. If they're aiming for photorealism, then all games will be aiming for the same look.
 
MavericK said:
People can't afford one GPU, let alone two. This is DOA if they can't get it performant on a single mid-range card.
Click to expand...
Yes, prices of GPUs are crazy these days.
I think this will get even worse. I believe we are seeing the end of days of one PC per person. PCs, and gaming PCs will be a rich man's toy. The great unwashed will have to rent a PC on the cloud. That's integral part of Agenda 2030. Prices will not come down
You'll own nothing a be happy, remember?
 
RedCharles9001 said:
I saw that too. It takes two 5090's to run this thing. Good grief.

I don't get all the hate though. This is pretty great.

As far as the claim, all games will look the same, well duh. If they're aiming for photorealism, then all games will be aiming for the same look.
Click to expand...
You obvious did not listen very carefully.
The presnetation was running 0n 2x 5090 because htey want no hickups.
They have it running on single GPU in the lab and come fall 2026 htat will become obvious.
 
leSLIe said:
Yes, prices of GPUs are crazy these days.
I think this will get even worse. I believe we are seeing the end of days of one PC per person. PCs, and gaming PCs will be a rich man's toy. The great unwashed will have to rent a PC on the cloud. That's integral part of Agenda 2030. Prices will not come down
You'll own nothing a be happy, remember?
Click to expand...
It's all part of the you will own nothing and be happy strategy.
 
leSLIe said:
No DLSS 5 for me...
I must have the "Artists Vision" 👇

View attachment 791861
Click to expand...

I honestly never gave a damn about artistic intent since I disagree with it like 90% of the time. Remember those piss yellow filters that every late 2000s game had? Yeah that was artistic intent. Or when HDR has significant black level raise in gameplay despite the fact that it can hit 0 nits black floor in cutscenes? Artistic intent. Or when games have film grain or sharpening filters that cannot be turned off from the graphics options? Artistic intent. Really I find the artistic intent in many games to be dogshit so I end up resorting to mods to adjust the visuals to how I like them.
 
T4rd said:
I'm not sure why people are clowing on it so much, it makes the lighting look much more realistic for sure. Maybe they can argue artists intent, but it's pretty clear in most of the examples shown that the artists are striving for realism to some degree at least.
Click to expand...
Because it looks like AI shit. I don't want to play what some vibe coded Nvidia slop dev thinks I should play, I want to play what game developers and artists wanted me to play. I don't know what was butchered more in the Resident Evil example, the character or the environment. The lighting mood of the scene was completely destroyed.

DLSS has been producing oversharpened image for some time now, which was bad enough, but at least it resembled the original. This? This is TikTok generation abysmal.
 
Meeho said:
I want to play what game developers and artists wanted me to play.
Click to expand...

Well good news then, the devs and artists will be the ones incorporating it into their games and adjusting the looks/parameters/output to what they think it should look like with it on.

Just make sure not to turn off DLSS5 or motion blur or chromatic aberration or something or you'll be ruining that 'dev/artistic intent' ☝️
 
Meeho said:
Because it looks like AI shit. I don't want to play what some vibe coded Nvidia slop dev thinks I should play, I want to play what game developers and artists wanted me to play. I don't know what was butchered more in the Resident Evil example, the character or the environment. The lighting mood of the scene was completely destroyed.

DLSS has been producing oversharpened image for some time now, which was bad enough, but at least it resembled the original. This? This is TikTok generation abysmal.
Click to expand...

Capcom was the one who set it that way, it wasn't like Nvidia just went in and changed their game then showcased it without them knowing. So Capcom themselves wanted you to play with Grace looking that way, not Nvidia.
 
MistaSparkul said:
Capcom was the one who set it that way, it wasn't like Nvidia just went in and changed their game then showcased it without them knowing. So Capcom themselves wanted you to play with Grace looking that way, not Nvidia.
Click to expand...
Then they enshitified their own product. Not the first time. The change is terrible.
 
Meeho said:
Then they enshitified their own product. Not the first time. The change is terrible.
Click to expand...

It looks off for sure but at the same time it's closer to her actual real life model so that's probably what they were after. Put them under the same exact lighting conditions and it would be even closer.
 

Attachments

  • IMG_2774.jpeg
    IMG_2774.jpeg
    244 KB · Views: 0
For all the whiners:
https://x.com/ryanshrout/status/2033686038829535318

I Just Saw DLSS 5 Running Across Multiple Games. It's Not a Face Filter.

NVIDIA just dropped DLSS 5 at GTC 2026, and the internet already has opinions.
I was in the room and I went hands-on. Not watching a sizzle reel, not scrubbing through a carefully curated 30-second trailer, but sitting in front of multiple games with DLSS 5 toggling on and off in real time. Hogwarts Legacy. Starfield. Assassin's Creed Shadows. Oblivion Remastered. The Zorah tech demo. The visual improvements are significant. Not incremental. Significant.
But if you've been scrolling social media, you'd think NVIDIA just shipped an Instagram beauty filter for video games. And I get why that's the first reaction. But it misses the true picture by a wide margin.

Why Faces Get All the Attention​

We've had photorealistic environments in games for a while now. Water reflections, volumetric lighting, incredibly detailed cityscapes and forests. The hardware and the rendering techniques have gotten us to a place where environments can look stunning under the right conditions.
But faces have been the holdout. Getting a human face to look truly photorealistic in real time has been one of the most expensive problems in computer graphics from a compute standpoint. Subsurface scattering on skin, the way light interacts with individual strands of hair, the micro-expressions that make a character feel alive rather than like a wax figure. All of that requires an enormous amount of rendering horsepower..
I've probably seen ten different "floating head" tech demos over the course of my career. That's not an exaggeration. They're always a single head with no hair, no body, no environment, because rendering a photorealistic face at that level of quality is so expensive that it can only be done in isolation. You never see it inside an actual game, because the performance budget won't allow it.


HDkZGdHbEAAwhdO?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
DLSS 5 closes that gap in a pretty dramatic way. And because that's the area where the delta between "before" and "after" is most visible, that's what everyone is reacting to. The NVIDIA team put it well during my demo. It's a psychological effect. You've seen environments rendered really well before. When you suddenly see a character rendered at that same photorealistic level, your brain flags it immediately. It stands out.


HDkZIxobEAIGdyc?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
Fair enough. But focusing only on the faces is wrong.

It's Happening Everywhere, Not Just on Character Models​

What I saw in the demos was a comprehensive improvement across the entire scene. And the moment that really drove this home wasn't a face. It was a coffee maker.
In Starfield, there's a countertop scene with a coffee machine, some paper towels, a cup, napkin holders. Standard environmental clutter. With DLSS 5 off, everything looks flat. The coffee maker fades into the background. Toggle it on, and suddenly the objects have shape. The lighting wraps around them naturally. The spatial relationships between the items and the surfaces they're sitting on become clear. It goes from "assets placed in a scene" to "objects that actually belong in a room."


HDkZeXGbwAAHJEF?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
The same thing played out across every title. In Oblivion Remastered, the water went from good video game water to something that could pass for real, with the kind of light interaction and shimmer you'd expect from an offline render. In Assassin's Creed Shadows, the trees and distant foliage gained dramatically better depth and separation in how light moved from the canopy down through the branches. In the Zorah tech demo, which is a 300 GB courtyard scene built by 20 full-time artists, the subsurface scattering on foliage was just as impressive as anything happening on character faces. Leaves picked up that translucent glow from backlighting that is incredibly difficult and expensive to model and render through traditional means.


HDkZhvobEAMkqb8?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
The AI model powering DLSS 5 is a single unified model. Same model for every game. It's not trained per-title, per-face, or per-object type. It takes the raw color buffer and motion vectors as input, analyzes the scene semantics from that single frame, and enhances the lighting and material response while staying anchored to the original 3D content. It recognizes the difference between skin and metal and water and stone and foliage, and it processes each of those materials differently based on how light should interact with them.
That's not a filter. That's a fundamentally different approach to how the final image gets assembled. And it's deterministic and consistent from frame to frame, which is a hard requirement for games.

The Developer Angle Matters More Than People Realize​

One of the things I came away most encouraged by is the developer control story. This is critical. If DLSS 5 were a black box that slapped a one-size-fits-all enhancement over every game, the artistic intent concerns would be completely valid. But that's not what this is.


HDkZrg6bEAECH4s?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
During the demo, the DLSS research talked through the level of granularity available. Developers don't just get an on/off switch. They get intensity controls that can be dialed anywhere, not just full strength. They get spatial masking, so they can set the water enhancement to 100%, wood to 30%, characters to 120%, all independently within the same scene. They get color grading controls for blending, contrast, saturation, and gamma. All of this runs through the existing SDK, which means studios already using DLSS and Reflex have a familiar pipeline to work with.


HDkZvR2aoAE00Qp?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
The developer support list tells you something. Bethesda, CAPCOM, Ubisoft, Tencent, Warner Bros. Games, and others have already signed on. But what struck me more than the names was what the NVIDIA team shared about the reactions inside those studios. When developers previewed the technology, their technical artists were apparently co-advocating for it internally, because it gets them closer to what they actually intended their characters and environments to look like when they were designing them in their authoring tools. Then those assets get dropped into a real-time game engine with a finite performance budget, and compromises happen. DLSS 5 lets them claw back some of what gets lost in that translation.
I think that's the right framing. DLSS 5 isn't NVIDIA applying its stylistic choices on top of someone else's game. It's providing a tool that helps developers close the gap between what they can render in 16 milliseconds and what they actually want the player to see. That's a meaningful distinction, and it's a big reason why the developer response has been positive.

The Hardware Story Is Interesting Too​

The demos I saw were running on a pair of RTX 5090 GPUs. One was handling the game rendering, the other was dedicated entirely to running the DLSS 5 AI model. NVIDIA was upfront that there's still significant optimization work to do, and the plan is to ship DLSS 5 running on a single GPU when it launches later this year.


HDkZ8G0bEAIpV2W?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
But I think the dual-GPU setup itself is worth mentioning. For years, multi-GPU gaming has been effectively dead. SLI is gone. CrossFire is gone. The idea that you'd run two graphics cards for a better gaming experience felt like a relic of the mid-2000s. And yet here we are, with a legitimate use case where a second GPU running an AI workload alongside a primary rendering GPU produces a dramatically better visual result.


HDkZ_14bEAIgT8P?format=jpg&name=900x900.jpg

Note: these are photos taken of a screen, so expect some glare/lighting impact.
Is that where this ends up for enthusiasts? Probably not at launch. But the concept of dedicating GPU compute specifically to AI-driven visual enhancement, separate from the rendering pipeline, is an interesting architectural idea. It wouldn't surprise me if that becomes a real conversation again as neural rendering matures.

Where This Goes From Here​

DLSS 5 is targeting a fall 2026 launch, which means we've got several months of optimization and refinement ahead. Developers are just getting their hands on it now, and they'll need time to work with the controls and dial in the right settings for their specific titles. First-wave games include Starfield, Assassin's Creed Shadows, Resident Evil Requiem, Hogwarts Legacy, Phantom Blade Zero, The Elder Scrolls IV: Oblivion Remastered, Delta Force, and more.
It's also worth noting that this works across rendering approaches. Rasterized games, ray-traced titles, and path-traced experiences all benefit. And the higher the fidelity of the input, the better the output. DLSS 5 isn't replacing good rendering. It's amplifying it.
The early social media reaction is predictable. New technology that changes how games look will always generate strong opinions, especially when AI is involved. But the knee-jerk "it's just a face filter" take doesn't hold up once you've actually seen the full scope of what DLSS 5 is doing across an entire scene, across multiple games, in real time. Go look at a coffee maker. Go look at stone textures. Go look at the way light passes through a leaf. That's where the real story is.
What do you think, is neural rendering the next big unlock for game visuals? I'd love to hear from people who have spent time with these games.
 
You must log in or register to reply here.
Back
Top