NVIDIA's recent DLSS 5 announcement was met with widespread controversy and backlash over how its AI model was built to deliver photorealistic lighting, producing visuals that look transformative, albeit with characters that cross into the uncanny valley. In response to the feedback, NVIDIA has reiterated that DLSS 5 doesn't alter in-game geometry and that it provides developers with the tools they need to fine-tune the effect to ensure it fits a particular game's art direction or artistic vision.

However, even though DLSS 5's technology is impressive from a purely technical level, that hasn't stopped the media and the PC gaming community alike from comparing the effects to an Instagram-like AI filter. Specifically, in the NVIDIA demos showcasing characters from games like Resident Evil: Requiem and Hogwarts Legacy, where characters look completely different. And with that, there aren't many positive comments surrounding DLSS 5, which makes this social media post from Kingdom Come: Deliverance 2 notable.
Daniel Vavra, who was the game director on the critically acclaimed 2025 story-driven action RPG set in 15th-century Medieval Europe, has taken a more pragmatic approach to DLSS 5's debut. Although he doesn't outright praise the DLSS 5 demos, he's optimistic about what it means for the future of gaming and how it might "replace" expensive ray tracing. Adding, "No way haters will stop this."
"I can imagine in the future devs will be able to train this tech for (a) particular art style or specific people(s) faces, and it might replace expensive raytracing etc," the post on X reads. "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."
Daniel Vavra is known for holding controversial opinions on a wide range of topics, so this defence of DLSS 5 is not out of character. However, it rightfully highlights that what we've seen so far is an early version of a new AI rendering technology that could be a game-changer for how expensive path-traced lighting is presented in games. Right now, DLSS 5 runs on a single catch-all model, similar to other DLSS technologies, so the note about training the model on a specific game's art and presentation could be key to living up to its promise of maintaining a game's unique or individual look.




