Tea Cozy
Explorer
Alright, we now have some official answers to what dlss5 is actually doing and tldr - it's doing exactly what the critics say it's doing. All the claims that it's taking in data from the renderer is just a lie. They're still trying to tapdance around the issue the best they can, but the questions asked here don't give them the wriggle room that their marketing speech has. By all means watch the video and read the officail responses yourself if you think I'm over reacting. If you like dlss5 fine, but don't try to gaslight others into believing it has anything to do with artistic intent, or that developers have control over the output.
What Nvidia told the YouTuber about frames is on their own website. It’s not new info.
NVIDIA DLSS 5 Delivers AI-Powered Breakthrough In Visual Fidelity For Games
NVIDIA DLSS 5 infuses pixels with photorealistic lighting and materials to bridge the gap between rendering and reality.
www.nvidia.com
The AI model is trained end to end to understand complex scene semantics such as characters, hair, fabric and translucent skin, along with environmental lighting conditions like front-lit, back-lit or overcast — all by analyzing a single frame. DLSS 5 then uses its deep understanding to generate visually precise images that handle complex elements such as subsurface scattering on skin, the delicate sheen of fabric and light-material interactions on hair, all while retaining the structure and semantics of the original scene.
DLSS 5 provides game developers with detailed controls for intensity, color grading and masking, so artists can determine where and how enhancements are applied to maintain each game’s unique aesthetic. Integration is seamless, using the same NVIDIA Streamline framework used by existing DLSS and NVIDIA Reflex technologies.
Plus, the YouTuber kept saying “unless I’m misreading this,” and I think he is. I think there is a fundamental misunderstanding going on about cosmetics here.
He showed the same image comparison I posted earlier, not the one that’s in the OP. He kept asking “how do we ask DLSS to remove the makeup it applied?” Thing is, it didn’t apply makeup that wasn’t in the original image.
In the original shot, Grace’s eyes are rimmed with black eyeliner both around the eyes and inside the rims. That is the original artistic intent, and the second shot keeps it.
What the second image doesn’t do is add blush and lipstick that did not exist in the first image. What it does is change her pallor, and even then, only slightly. Note I am not talking about skin tone. Grace simply looks a bit more human.
If the complaints were that Grace needs to look less hale for artistic reasons, then I’d understand better where they’re coming from. I also think it is something that can be corrected on the developer end.
However, the YouTuber claims she looks dressed up for a night out with a full face, which puts me in fact-checking mode once again. Is it because cream blush looks so subtle these days people can’t tell the difference between it vs natural skin coloration?
Last edited:







