In its full GDC 2026 session outlining the future of Path Tracing, Nvidia’s Martin Stich talked about how one non-gameplay scene (based on assets provided by CD Projekt RED) featured 60 million plants and one million trees across a 5×5 km terrain. Despite featuring 200 different plant species and some trees having more than 10 million polygons, it loads without any streaming.

All of this is complete with fully path-tracing lighting. Perhaps the most impressive part of all this is that it runs at 4K/80 FPS, but there are some caveats. It’s running on an RTX 5090, and the 4K resolution is upscaled from 1440p with DLSS Quality mode. Comparatively, an RTX 4070 would eke out 58 frames at 1440p (upscaled from 960p).

As noted previously, none of this represents the actual gameplay or the hardware you’ll need to run The Witcher 4 on PC. At this point, it’s a cool tech demo of what RTX Mega Geometry is capable of using the game’s assets. Whether it reaches this level of fidelity and complexity remains to be seen, so stay tuned.

The Witcher 4 doesn’t currently have a launch date, though there are claims of a late 2027 launch. Officially, it’s still in full production with CD Projekt RED recently scaling up its team (among others) for the same.

“I can imagine in the future devs will be able to train this tech for particular art style or specific people faces and it might replace expensive raytracing etc.,” he wrote. “This is just a little uncanny beginning. No way haters will stop this. It’s way more than a soap opera effect every tv has when you turn motion smoothing on.”

It is worth noting that this is far from the first time Vávra has said positive things about AI-based technologies. Back in December, he took to social media to discuss how “AI hysteria” has been getting out of hand in light of at-the-time discussions about the role of generative AI in game development.

“I’m no fan of AI generated art, but anyway, it’s time to face reality,” wrote Vávra. “AI is here to stay with us. As frightening as it may be, that’s the way it is. Personally, it scares me the most in the music because you can’t even recognise AI there anymore.”

Vávra went on to discuss potential use cases of generative AI tools, which have the potential to remove some of the more tedious aspects of game development. He brought up things like having to “spend 500 hours in the studio recording completely generic heckling and generic bars.”

“If AI can help me make an epic game in a year with a smaller team like in the old days, I’m all for it,” he wrote. “That game will still have an art director, writers, programmers, graphic designers, but they won’t have to do the tiresome and boring tasks, they’ll have to focus on the essentials. I have ideas for lots of games, but I’m fifty years old and so far it’s taken me seven years on average to make one game. If AI helps me realize those ideas faster, I’m all for it.”

On the other hand, DLSS 5 has faced criticism from many other game developers. Among these was veteran animator on games like God of War Ragnarök and Death Stranding 2: On the Beach, Mike York, who noted that “this isn’t just some lighting.”

“No, no, no, no, no, no, no, no, no, no,” he exclaimed while analyzing the Resident Evil Requiem showcase. “No. This isn’t just some lighting, dude. What the f–… I’m telling you, this is like a complete AI re-render.”

“Who even is that? That’s a different girl,” York continued. “You know why I can tell […] – look, her eyes are no longer looking, like, correctly. That one eye is looking over here, and one eye is looking there. And it rendered the eyes differently. And you can also tell that it’s… how do I say this… it has somehow put wrinkles into her lips that weren’t there before… it’s added all kinds of details that were not there before.”

“They’re literally re-rendering this completely, frame by frame. You’re no longer looking at the game anymore, does that make sense? This is scary.”

DLSS 5 is slated for launch later this year for Nvidia GeForce GTX 50-series graphics cards. Take a look at how Nvidia CEO Jensen Huang has been defending the technology. Also check out how developers and artists from Capcom and Ubisoft were left in the dark about the showcase.

Well, that’s just what we’re here to do as we dive in to what’s good and what’s not about DLSS 5’s AI-powered upscaling abilities, and give you our opinion on whether the latest iteration of a feature that’s been around for a while is going to take away the autonomy of developers who use it.

We’re looking beyond the memes and mockery on what was supposed to be a major leap in graphics for modern games, but instead devolved into a PR disaster that NVIDIA would rather have avoided. But as things stand, the company could have done better to introduce it in a way that didn’t automatically cause derision and distrust. How, you ask? Join us and find out.

The Basics

Let’s get done with the basics first. In this section we will talking about what we know about the situation, gamers’ reaction and Nvdia’s response. So, what is DLSS5? An abbreviation for deep learning super sampling, DLSS 5 is merely the latest iteration of NVIDIA’s real-time neural rendering model that’s quite handy when it comes to enhancing lighting and materials in games. It reportedly includes a suite of controls that make things easier for developers to ensure that a game’s artistic vision is properly implemented, allowing for artists to decide on important parameters in the scenes they are trying to create.

It’s the artists who ultimately decide where and how it’s applied, and it isn’t being pitched as a one-click beauty filter as many of us have been led to believe by the outrage over its implementation in showcases.

With that out of the way, let’s dive into the heart of the controversy: reports that DLSS 5 is trying to override developers and artist’s vision for the games they work hard to create.

It’s crucial to address why DLSS 5 has gamers worried about the new tech. Some believe that the tech is going to be forced into modern games against the wishes and visions of their creators. That’s apparently not the case, and NVIDIA has been quick to try addressing that particular facet of the conversation.

It has since clarified that it is the studios who retain control over its implementation, a position further reinforced by a supporting assertion from Bethesda who have since argued in favor of it. It’s going to be under the control of artists and creators, and completely optional for players. That’s all well and good, but what has caused the tech’s reveal to draw the ire of such a huge chunk of the gaming community?

Well, that might be on NVIDIA, and it’s decision to showcase the tech in action on games that were already widely known and recognizable by the public. Take the widely circulating photo of Grace in Resident Evil Requiem, for instance. We must admit she did look quite different from her appearance in the game, and the same can be said for showcases in other games like Starfield and Hogwarts Legacy.

The adverse reactions to DLSS 5 didn’t come from abstract white papers on what the tech could do, or related SDK documentations. They came from noticeable shifts to lighting, faces, and tone in games that they knew and loved, their emotional bonds to their experiences coming into conversation with worries about AI and its implementations in modern gaming. It came across wrong, looking more like AI-fuelled restyling rather than developer-focused enhancement.

In its eagerness to show off just how good DLSS 5 could be, and the advantage it would give developers as they made new titles, NVIDIA failed to duly consider an important facet of keeping its fan base engaged: trust.

NVIDIA’s fervor to unveil a piece of tech that probably comes with benefits (which by the way isn’t clear yet) failed to properly address concerns that are rooted in a deep mistrust of AI, and its documented impact on development processes in video games.

In a world where layoffs due to AI implementations already have people on edge, the question of whether audiences can trust neural rendering software to serve the vision of its developers comes into play, and it’s one that NVIDIA should have accounted for. Previous iterations of DLSS haven’t whipped up a debate as fierce as this one, after all, even though there have been conversations about upscaling, frame generation, and ghosting in the past.

Somehow, DLSS 5 has raised the issue of aesthetic ownership, and has made players wonder about how the tech could gradually reshape games into experiences that are far removed from what they were originally intended to be. And the tech’s rollout might have just made things worse.

We’ve already spoken about how showcasing it in games that players were already familiar with invited ridicule and criticism. Those before and after comparisons are all over the internet now, and it’s easy to see why there would be concerns about the tech overriding what a studio originally intended for a game.

NVIDIA’s no-holds-barred approach to defending the tech is another factor. While they can probably see where they were coming from in his assertion that the criticisms levelled against DLSS 5 were “completely wrong”, but from a personal, more emotional note, their arguments conveyed a dismissive attitude towards what players believed were valid points they were making against a feature that they believed would take value away from the games DLSS 5 was meant to enhance.

It’s a good idea to look deeper at both sides of this argument at this junction.

The Two Sides

Let’s start with what DLSS 5’s critics are saying about it. These are all valid complaints, starting with concerns about the tech homogenizing different games across genres, giving them an AI-powered look that could be seen as a way to impose NVIDIA’s own ideas about how a game should look over the artistic visions of the studios that create them.

In the case of Grace from Requiem, the tech seemed to completely change her look, giving her a sort of “exaggerated” glow-up that seemed far removed from her look in the actual game. It further reinforced fears that the tech could make games look like what NVIDIA dictated they should look like considering that it owns the software.

Nvidia’s defense might not have addressed those fears satisfactorily enough, but the reports that it was a controllable and deterministic tool that was going to operate off of a game’s own 3D framework shows that DLSS 5 is far more than a sort of black-box beautification filter,

It’s more of a way to grant developers generative control at the geometrical level as opposed to a post-processing filter that operates on the frame level. However, all of these important nuggets that lend credence to Nvidia’s defense have been overridden by their apparent blunt dismissal of valid concerns.

Bethesda, who took on a more placatory position, by asserting that the tech was still in its early stages while also reiterating that it was a tool that left control of its implementation completely in the hands of its developers.

In Bethesda’s response to the entire DLSS 5 episode, there was one simple component that stood out. As a studio that has earned the goodwill of its fans over the years (and badwill recently), it seemed far better poised to attempt assuaging their fears. Whether it worked is a different topic altogether.

Which brings us to our own position on the subject.

Striking A Balance

We believe NVIDIA’s demo strategy should have accounted for concerns about AI taking over the creative vision of games that it’s powering, no matter how sensible those concerns were. In failing to do so, it created the situation it now faces.

But that doesn’t mean that reports about the tech taking visual control away from developers shouldn’t be taken as seriously as they have, especially in the light of public statements to the contrary. We’re not saying there’s no reason to be wary, because there absolutely is. The current demos do an absolutely pathetic job of enhancing the games, thereby destroying the art style of those products. On the other hand, let these companies deliver actual real time implementations in games running on retail platforms first. We’ll be in a much better position to judge the results then.

And the whole thing needed a bit of nuance from Nvidia. Is it that hard, Nvidia? The tech exists, and reportedly it’s quite flexible as things stand. The onus is now on NVIDIA to ensure that its true potential comes across in a way that’s able to convince us gamers, and the best way to do that is to show us what it looks like when it’s fully utilized by talented studios in the final release build of an excellent game, rather than static moving screens which look like AI face filters.

Note: The views expressed in this article are those of the author and do not necessarily represent the views of, and should not be attributed to, GamingBolt as an organization.

“I think their perspective makes sense and I can see where they’re coming from, because I don’t love AI slop myself,” said Huang on the subject of backlash against DLSS 5. “You know, all of the AI generated content increasingly looks similar and they’re all beautiful. So, I’m empathetic towards what [critics] are thinking.”

As for how DLSS 5 functions, however, Huang made a note of the technology being “3D conditioned, 3D guided.” This, he said, means that artists have complete control over the in-game geometry, which is then used by DLSS 5 to generate its visuals.

“I showed several examples of it, but DLSS 5 is 3D conditioned, 3D guided. It’s ground truth structure data guided. And so the artist determined the geometry, we are completely truthful to the geometry in every single frame,” he said.

This isn’t the first time that Huang has spoken out against the backlash to DLSS 5. Earlier this month, he was asked about the technology’s reception among the larger gaming audience by Tom’s Hardware editor-in-chief Paul Acorn. He responded by calling critics “completely wrong”.

“Well, first of all, they’re completely wrong,” Huang said. “The reason for that is because, as I have explained very carefully, DLSS 5 fuses controllability of the geometry and textures and everything about the game with generative AI.” He also reiterated that developers can “fine-tune the generative AI” depending on the kind of output they want, and 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.

Discussing the fact that developers can go as far as coming up with a “toon shader” or a game where everything is “made of glass,” and continue to have power over the DLSS 5 development kit. “All of that is in the control — direct control — of the game developer,” he explained. “This is very different than generative AI; it’s content-control generative AI. That’s why we call it neural rendering.”

More details about how DLSS 5 works were revealed by Jacob Freeman as part of an interview where he was asked about how the technology was trained, and how it handles things like PBR (physically based rendering) materials. In this discussion, Freeman confirmed that DLSS 5 takes a 2D image of a game, along with its motion vectors, as its input to then output its own image.

As for how the technology makes significant changes to things like characters – as seen with the Resident Evil Requiem example in the original showcase – Freeman didn’t offer too much information. Rather, he simply said that “the underlying geometry is unchanged. Also worth mentioning this is a very early preview of the tech.”

For more on DLSS 5 and its backlash, take a look at what journalists and developers have said. Also check out the report indicating developers and artists from Capcom and Ubisoft were left in the dark about the technology.

The questions asked by Owen all revolve around the fact that DLSS 5 works by taking 2D frames, along with motion vectors, as the input to then generate an output frame. Freeman confirmed this in his response. The discussion then went into whether DLSS 5 just takes a 2D image of a game and “reinterprets” it, comparing the idea to asking an AI model to enhance any given screenshot from the game.

Freeman said that the technology has been trained by Nvidia to “understand complex scene semantics,” ranging from materials like hair and fabric, to entire entities like characters and background objects, as well as environmental lighting conditions. However, all of this understanding comes from the analysis of a single frame.

On the subject of whether DLSS 5 can actually make significant changes to things like character designs. Owens uses a screenshot from the showcase’s Starfield example, noting that the character’s hairline was noticeably altered by DLSS 5. Similarly, he also brought up how Resident Evil Requiem‘s Grace Ashcroft had make-up added to her face. To this, Freeman simply responded that “the underlying geometry is unchanged. Also worth mentioning this is a very early preview of the tech.” This response essentially indicates that Nvidia is only discussing the fact that the game’s model geometry isn’t changed, and isn’t actually referring to how DLSS 5 alters characters’ features.

Similarly, DLSS 5 doesn’t seem to take in any input from artists about the state of PBR materials. Rather, the technology essentially infers what it can about the state of various materials in a game scene through the frame and motion vectors it takes in. “Materials are inferred from the rendered frame,” explained Freeman. As for how the tech, as Freeman put it in an earlier email, “enhances PBR properties on materials (roughness, more realism), with more realistic interaction of light,” however, Owens noted this as being a bit misleading.

While Nvidia has noted that developers and artists will have control over three core aspects of DLSS 5—intensity, color grading and masking—whether they will have finer control over things, like simply not wanting additional make-up applied to a character is currently unknown. Rather, Freeman reiterated the three core methods of controlling DLSS 5, noting that “developers can also mask specific objects or areas to be excluded from enhancement.” This essentially means that, short of singling Grace out in the Resident Evil Requiem example from working with DLSS 5 entirely, developers don’t seem to have options like “disable make-up” available to them.

“We continue to talk to developers to understand all the ways they would like to control the technology,” he said. “Ultimately, we see DLSS 5 as a tool for them to achieve their artistic vision, rather than be limited by the capabilities of traditional real-time rendering.”

Digging further into the idea of DLSS 5 working off a single frame rendered by the game, Owen also asked whether the technology could work on off-screen objects. Unfortunately, Freeman couldn’t answer this, once more reiterating that it only takes the on-screen visuals and motion vectors from a single frame as input.

For more on the DLSS 5 saga, take a look at what an animator for Death Stranding 2: On the Beach has to say about the technology. Also check out a report that indicates that developers were essentially left in the dark about the technology before the showcase went live. In response, Nvidia CEO Jensen Huang has been on the defensive, saying that critics are “completely wrong” about DLSS 5.

On seeing Grace’s transformation for the first time, York seemed to be visibly dumbstruck, saying “Whoa, hold on” as he more carefully analyzes the changes. He went on to note that the changes made by DLSS 5 are quite radical rather than simply being upgraded lighting. Instead of simply being improvements, he referred to it as being “like a complete AI re-render.”

“No, no, no, no, no, no, no, no, no, no,” he exclaimed. “No. This isn’t just some lighting, dude. What the f–… I’m telling you, this is like a complete AI re-render.”

“Who even is that? That’s a different girl,” York continued. “You know why I can tell […] – look, her eyes are no longer looking, like, correctly. That one eye is looking over here, and one eye is looking there. And it rendered the eyes differently. And you can also tell that it’s… how do I say this… it has somehow put wrinkles into her lips that weren’t there before… it’s added all kinds of details that were not there before.”

“They’re literally re-rendering this completely, frame by frame. You’re no longer looking at the game anymore, does that make sense? This is scary.”

In its own statement, Nvidia had noted that developers and artists would have complete control over how DLSS 5 changes the looks of various scenes and characters. The company argued against the idea that the technology was simply an “AI filter” on top of the game’s own visuals. Rather, DLSS 5 seemingly uses information from the game for each individual frame.

“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,” wrote the company. “The SDK includes things like intensity, color grading and masking off places where the effect shouldn’t be applied. It’s not a filter – DLSS 5 inputs the game’s color and motion vectors for each frame into the model, anchoring the output in the source 3D content.”

Nvidia CEO Jensen Huang has also been on the defensive since DLSS 5 was first unveiled. When asked about the technology, he said that critics are “completely wrong. The reason for that is because, as I have explained very carefully, DLSS 5 fuses controllability of the geometry and textures and everything about the game with generative AI.”

A report has indicated that developers and artists from Capcom and Ubisoft were left in the dark about the DLSS 5 presentation. One unnamed Ubisoft developer even revealed that they only learned about the technology when the rest of the world did – during Nvidia’s showcase.

“We found out at the same time as the public,” said one developer for Ubisoft. The report went on to note that Capcom’s developers were particularly shocked with the company’s involvement with DLSS 5. They described the company as traditionally being quite “anti-AI” for the development of games like this year’s Resident Evil Requiem. There have also apparently been fears about the showcase leading Capcom leadership to change its mind about AI technology and force its implementation into in-development games.

Curiously, the report comes in light of senior director of Global PR of GeForce at Nvidia, Ben Berraondo, taking to social media to say that the inclusion of Resident Evil Requiem in the DLSS 5 showcase was done in collaboration with Capcom, and that the studio’s own team had worked on it. “Game developers have detailed artistic control,” he said.

DLSS 5 was unveiled earlier this week, and almost immediately started facing criticism from journalists as well as developers. According to Nvidia, the technology “takes a game’s color and motion vectors for each frame as input, and uses an AI model to infuse the scene with photoreal lighting and materials that are anchored to source 3D content and consistent from frame to frame.”

“Bridging the divide between rendering and reality, DLSS 5 empowers game developers to deliver a new level of photoreal computer graphics previously only achieved in Hollywood visual effects.”

Many have called out the changes made by the technology to various characters as essentially being like AI-generated images turning “everyone into yassified, looks-maxed freaks,” as noted by Noclip’s Danny O’Dwyer. RPGSite’s Alex Donaldson called the effect “uncanny & weird”, and noted that artistic expression was at risk.

When asked about this, Nvidia CEO Jensen Huang had his own statement, saying that everyone criticising DLSS is “completely wrong”. He went on to say that, “The reason for that is because, as I have explained very carefully, DLSS 5 fuses controllability of the geometry and textures and everything about the game with generative AI.”

“It’s not post-processing, it’s not post-processing at the frame level, it’s generative control at the geometry level,” he continued after noting that developers and artists will have plenty of control over the outputs of DLSS 5.

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

The level of control was further expanded on by Nvidia through a pinned comment under its DLSS 5 Showcase, where it said: “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.”

“The SDK includes things like intensity, color grading and masking off places where the effect shouldn’t be applied. It’s not a filter – DLSS 5 inputs the game’s color and motion vectors for each frame into the model, anchoring the output in the source 3D content.”

DLSS 5 doesn’t yet have a release date. It is slated to come to all GeForce RTX 50-series GPU users later this year.

“Well, first of all, they’re completely wrong,” Huang said. “The reason for that is because, as I have explained very carefully, DLSS 5 fuses controllability of the geometry and textures and everything about the game with generative AI.” Further in his statement, he noted that developers will continue to have power to “fine-tune the generative AI” according to the output they want, and 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 has also confirmed that developers will be able to configure DLSS 5’s development kit to come up with a “toon shader” for a less photo-realistic style, or if the game should look like everything is “made of glass”.

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

Huang’s statement echoes Nvidia’s own pinned comment under the YouTube video of its DLSS 5 showcase. The company noted that DLSS 5 won’t simply be an “AI filter” applied on top of a game’s visuals. Instead, the technology will be able to make use of information it gets directly from the game before outputting new visuals.

“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,” wrote Nvidia. “The SDK includes things like intensity, color grading and masking off places where the effect shouldn’t be applied. It’s not a filter – DLSS 5 inputs the game’s color and motion vectors for each frame into the model, anchoring the output in the source 3D content.”

Among the games used by Nvidia to showcase DLSS 5’s features was Resident Evil Requiem, with comparison screenshots immediately facing plenty of criticism from journalists and developers alike. Noclip’s Danny O’Dwyer took to social media platform BlueSky to call the technology out for producing “yassified, looks-maxed freaks.” Concept artist Jeff Talbot similarly noted that, “This is NOT the direction games should be going in. In every shot the art direction was taken away for the senseless addition of ‘details’. Each DLSS 5 shot looked worse and had less character than the original. This is just a garbage AI Filter. Lets not do this s***.”

DLSS 5 is slated to arrive on Nvidia’s RTX 50-series graphics card later this year. However, Nvidia hasn’t yet announced a release date for it yet, and the company is still working on further optimize it to run on a wider range of hardware.

Among the controls offered to developers through the software development kit for DLSS 5 include intensity, color grading, and the option to add masks in places where the effects shouldn’t be applied. Along with this, the company has also argued against the idea that DLSS 5 is simply an “AI filter” applied on top of the game’s visuals. Rather, the technology makes use of information it gets from the game for each one of its frames before generating the new visuals.

“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,” wrote Nvidia. “The SDK includes things like intensity, color grading and masking off places where the effect shouldn’t be applied. It’s not a filter – DLSS 5 inputs the game’s color and motion vectors for each frame into the model, anchoring the output in the source 3D content.”

In its showcase of DLSS 5’s capabilities, Nvidia had used a number of games, including Resident Evil Requiem. However, the company came under fire for how the technology was making changes to protagonist Grace Ashcroft’s facial features, which some even called out as being “yassified.”

Among the critics is Noclip’s Danny O’Dwyer, who took to social media to write, “Weird that this impressive lighting tech also randomly turns everyone into yassified, looks-maxed freaks. it’s like all this technology can’t help itself but sexualize everything it touches. but like, through the lens of teenage boys.”

Game developers have also been calling out the technology. Concept artist Jeff Talbot said, “This is NOT the direction games should be going in. In every shot the art direction was taken away for the senseless addition of ‘details’. Each DLSS 5 shot looked worse and had less character than the original. This is just a garbage AI Filter. Lets not do this s***.”

Nvidia has described DLSS 5 as being able to take the color and motion vectors from each frame of a game as input, and making use of an AI model to “infuse the scene with photoreal lighting and materials that are anchored to the source 3D content and consistent from frame to frame.”

“Bridging the divide between rendering and reality, DLSS 5 empowers game developers to deliver a new level of photoreal computer graphics previously only achieved in Hollywood visual effects,” claimed the company.

Since Starfield was one of the games showcased in the presentation, Bethesda has offered its own thoughts on the matter, noting that “our art teams will be further adjusting the lighting and final effect to look the way we think works best for each game.” The company went on to reaffirm that it will be completely under the control of artists, and entirely optional for players.

While technically quite impressive, since DLSS 5 is seemingly capable of generating just about every frame for a game on the fly based on the output of the GPU, the aesthetic choices being made by the technology has been the subject of plenty of criticism.

“DLSS 5 takes a game’s color and motion vectors for each frame as input, and uses an AI model to infuse the scene with photoreal lighting and materials that are anchored to source 3D content and consistent from frame to frame,” explained Nvidia as part of its announcement.

“Bridging the divide between rendering and reality, DLSS 5 empowers game developers to deliver a new level of photoreal computer graphics previously only achieved in Hollywood visual effects.”

Among the critics of DLSS 5 has been Noclip’s Danny O’Dwyer, who took to social media platform BlueSky to describe the technology as randomly turning “everyone into yassified, looks-maxed freaks.” One of the key examples used by Nvidia to showcase the feature was Resident Evil Requiem protagonist Grace Ashcroft, whose look has been radically altered to also include a heavy use of make-up, as well as subtle changes to her overall face structure.

RPGSite’s Alex Donaldson similarly criticised the DLSS 5 effect as being “uncanny & weird,” and noted that the technology poses a risk of squeezing out artistic expression during the development process of a game. “I wonder how much devs can get in and tweak the model to their artistic intent,” he wrote.

Game developers also seem to not be happy with the showcase. Respawn Entertainment’s rendering engineer Steve Karolewics noted that DLSS 5 seems to change how the characters from the games look a bit too much.

“DLSS 5 looks like an overbearing contrast, sharpness, and airbrush filter,” he wrote, according to VideoGamesChronicle. “Remarkably different frames with the rationale of photo-real lighting? Nah, I think I’ll stick with the original artistic intent.”

Concept artist Jeff Talbot went as far as to say that, “This is NOT the direction games should be going in. In every shot the art direction was taken away for the senseless addition of ‘details’. Each DLSS 5 shot looked worse and had less character than the original. This is just a garbage AI Filter. Lets not do this s***.”

Interestingly, Bethesda has offered its own statement on the matter, saying that its art teams will be adjusting the lighting and final effect to ensure that Starfield looks good. The company also noted that any changes made by DLSS 5 would be “under our artists’ control, and totally optional for players.”

“Appreciate your excitement and analysis of the new DLSS 5 lighting here,” wrote the company on X. “This is a very early look, and our art teams will be further adjusting the lighting and final effect to look the way we think works best for each game. This will all be under our artists’ control, and totally optional for players.”

DLSS 5 is slated to be available on Nvidia’s GeForce RTX 50-series graphics cards later this year.