Nvidia’s recent DLSS 5 announcement caused quite the stir in various tech and gaming spaces, and that’s not necessarily a good thing. Any press is good press, one might say, but in this case, most of the conversation on social media has been centered around what DLSS 5 does to in-game assets. Most importantly, the faces of various characters.

The “AI slop” label has been plastered all over DLSS 5, and I’m not here to debate whether that should be the case or not. I’m only here to remind you that if you’re focusing on that aspect of DLSS, you’re missing out on the part that actually matters.

DLSS 5 stole the headlines

And not in a good way

Don’t you just love it when the PC gaming/hardware enthusiast community has a meltdown about something or other? It happens regularly, which isn’t unexpected, given that we all care about the matter at hand and hardware tends to be expensive. Don’t even get me started on GPU prices.

With that in mind, I wasn’t surprised when Nvidia’s DLSS 5 announcement absolutely dominated the headlines. And, given the contents of the update, I also wasn’t too shocked when the general public responded negatively.

After all, DLSS 5 is controversial. It departs from Nvidia’s usual goal for the software stack, which is performance improvement, in a major way. And it gives games an AI-powered facelift that many gamers never asked for.

Officially, Nvidia is pitching DLSS 5 as a much bigger shift than another round of upscaling tweaks. The company says DLSS 5 uses a real-time neural rendering model that takes a game’s color and motion-vector data and then adds more photorealistic lighting and material detail, with specific callouts for things like skin, hair, fabric, and more complex light interactions. Nvidia also says developers get control over intensity, color grading, and masking, and that DLSS 5 itself is scheduled to arrive this fall rather than right away.

DLSS 5 comes with some important caveats

The over-the-top faces aren’t its only problem

Technical details aside, DLSS 5 serves up what many refer to as “AI slop.” It turns in-game assets, chiefly characters’ faces, into a completely different version of what the devs had there to start with. Everything is different, and it’s not just the fact that frames are changing; the lighting is off, too.

While DLSS 5 sounds impressive on paper, the public reaction ​​​​​​hasn’t been great. Nvidia’s own preview video is currently flooded with comments made by people who are making fun of the tech or mourning the loss of originality in games. This was brought on by footage from games like Resident Evil Requiem and Starfield, where faces looked unnaturally polished, overly homogenized, or just plain uncanny, which is where the whole “AI slop” criticism really took off.

The negative reaction was strong enough that Nvidia stepped in, saying in the comments: “Important to note with this technology advance – game developers have full, detailed artistic control over DLSS 5’s effects to ensure they maintain their game’s unique aesthetic.”

There are also some practical caveats here beyond the uncanny valley-esque faces.

For one thing, DLSS 5 is a visual fidelity feature and not a straightforward performance tool. It runs in real time at up to 4K, but it’s almost guaranteed to have a performance overhead as a result. Early reporting suggests this isn’t exactly a lightweight effect, and no surprise. This is a neural-rendering step that adds lighting and material changes on top of the existing frame rather than just chasing higher fps the way many people expect from DLSS.

It’s also locked to the RTX 50-series, so many people won’t have to try hard to avoid it; they simply won’t have access to it in the first place.

Dynamic multi-frame gen is what truly matters

Surprisingly, it’s not even part of DLSS 5

Credit: 

Justin Duino / How-To Geek

All the talk around DLSS 5 has drowned out the fact that, at its most basic level, it doesn’t really fit with the rest of Nvidia’s software stack. It’s hard to compare it to the other iterations, and Nvidia’s had a lot of success with DLSS the way we’ve grown to expect it to be: a performance-related tool.

Announced at CES 2026, DLSS 4.5 delivers Dynamic Multi-Frame Generation and 6x MFG. And if that announcement came bundled with the updates provided by DLSS 5, maybe the reaction would’ve been more accepting.

Dynamic frame gen is a pretty fantastic addition. It’s designed to react to changing workloads and balance frame rate, image quality, and responsiveness on the fly. DLSS 4.5 in and of itself may not boost frame rates by much (although some have noted gains of up to 10% in certain titles), but it lets you crank up the quality-related settings in DLSS and still maintain good performance.

Then, there’s 6x multi-frame generation. The benefits here are obvious, and will be even more pronounced than the previous iterations of DLSS.

Nvidia accidentally proved what gamers really want from AI

It’s not the face filters, apparently

Credit: Hannah Stryker / How-To Geek

DLSS 5 is, in a way, groundbreaking. We’ve all grown accustomed to AI-generated videos and images, and the quality of both is now so good that it’s sometimes hard to tell the difference between reality and AI. But to apply that to gaming in real time, and with the results Nvidia showed off, is huge.

And yet, it’s not really what gamers want.

I think there’s probably a level of uncanny valley and realism that gamers want from their gaming, or at least that is the case for me. I don’t need my in-game characters to look like real people (or better). I want them to look cohesive, to fit into the game worlds they were created to fit into, and to have their own, aesthetically pleasing visuals. And that can truly mean anything from Stardew Valley graphics to Cyberpunk 2077 on RT Overdrive settings. It just needs to work together.

Is DLSS 5 as bad as it seems?

It’s too early to say how good, or bad, DLSS 5 is going to be. It’s possible for it to be both groundbreaking and disappointing all at once, but so far, I think that the main focus should be the immediate gains of DLSS 4.5. For DLSS 5, it’s all still very early days; by the time it’s actually out, we might be happier with the end result. Let’s hope.

Graphics RAM Size

12GB

Brand

ASUS

Architecture

NVIDIA Blackwell

If you want to give DLSS 5 a try, you’ll need an RTX 50-series graphics card, and it needs to be one that can handle the compute tax. The RTX 5070 is a midrange GPU that bridges the gap between “too weak” and “too expensive.”