Just months after announcing DLSS 4.5 at CES, NVIDIA has unveiled its next major upscaling technology, DLSS 5. The company is doubling-down on AI for this next iteration, claiming DLSS 5 “infuses pixels with photoreal lighting and materials” using a real-time neural rendering model when it arrives this fall.

So what does this mean in practice? In an on-stage demo at NVIDIA’s GTC 2026 keynote, CEO Jensen Huang showed off the technology with Resident Evil: Requiem, Hogwarts Legacy and Starfield. DLSS 5 adds a noticeable amount of detail to character’s hair and skin tone, but it also appears it’s being compared to those games without any DLSS features turned on. It’s unclear how much of a difference it makes compared to DLSS 4.5 with path tracing and all of its features turned on.

“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,” NVIDIA said in a blog post. The company also notes that the technology runs in real time, and it works at up to 4K.

Huang showed off DLSS 5 while running a system with two RTX 5090 GPUs. Eventually, it will be able to run on a single video card (though I’d imagine it would have to be almost as powerful as two 5090s). Huang also paints DLSS 5 as a step towards offering Hollywood-like quality for real-time rendering, without the need for the GPU horsepower required by studios. It sounds a bit like a generative AI video model that can be directly controlled by developers, instead of just AI prompts.

NVIDIA, never shy from self-aggrandizing, claims DLSS 5 is also the “biggest breakthrough in computer graphics” since real-time ray tracing arrived in 2018. But given that ray tracing itself hasn’t been mainstream for many gamers, it’ll be interesting to see if there’s any interest in NVIDIA’s AI-produced pixels.