DLSS 5: Has Nvidia’s AI graphics technology gone too far?

Nvidia has revealed a new “3D guided neural rendering model” called DLSS 5 that can change a game’s lighting and materials in real-time, and… many gamers aren’t happy. From DLSS 5 memes to complaints about how it’s “yassified” Resident Evil Requiem characters in demos, the first impression has not been a good one, no matter how much Nvidia insists that this pursuit of photorealism is still honoring the original artists’ intent.

Nvidia surely thought it was doing a good thing for gamers by “upgrading” the faces of our favorite video game characters. But that just shows how much the company has lost the plot. Nvidia could’ve marketed its new DLSS 5 real-time lighting technology as a way to make future, next-gen games look better. Instead, it told the world that games people already know and love look bad. It focused on retconning characters’ faces. And now, confronted with the predictable backlash, Nvidia’s CEO is telling critics that we’re “completely wrong.”

“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 said, noting that developers can “fine-tune the generative AI.” Yesterday Nvidia revealed its latest upscaling tech, called DLSS 5, which it described as “the company’s most significant breakthrough in computer graphics since the debut of real-time ray tracing in 2018.”

According to Nvidia, the tech “infuses pixels with photoreal lighting and materials,” but all anyone seemed to notice was that it turned recognizable faces into something resembling AI slop. Resident Evil Requiem protagonist Grace got a makeover that would make her look at home in a filtered video. The Hogwarts Legacy kids looked like they’d been wrung through an Instagram filter. Even Liverpool captain Virgil van Dijk had his features warped and became just some other dude with DLSS 5. This “significant breakthrough” imbues everything with a particular look that’s become synonymous with AI-generated art.

Nvidia CEO Jensen Huang is calling this the “GPT moment for graphics — blending hand-crafted rendering with generative AI to deliver a dramatic leap in visual realism while preserving the control artists need for creative expression.” In games that support DLSS 5, the tools can immediately provide noticeable boosts to lighting and shadows, but unlike previous versions of upscaling that used machine learning to close the gap between high and low graphics settings, this version applies generative AI to rework the lighting and materials with details that feel newly added.

Nvidia’s real-time neural rendering model is coming this fall with support from Bethesda, Capcom, Hotta Studio, NetEase, NCSoft, S-Game, Tencent, Ubisoft and Warner Bros. Games to start.