NVIDIA Deep Learning Super Sampling DLSS

NVIDIA DLSS (Deep Learning Super Sampling) is a neural graphics technology that multiplies performance using AI to create entirely new frames and display higher resolution through image reconstruction—all while delivering best-in-class image quality and responsiveness.

Explore the Benefits of DLSS

Performance Multiplier

The AI network analyzes sequential frames and motion data to create additional high-quality, responsive frames.

Uncompromised Quality

Advanced super-resolution temporal image reconstruction produces images comparable to or better than native resolution while rendering a fraction of the pixels, letting you maximize frame rate.

AI That Improves

DLSS takes advantage of AI models that are continuously improved through ongoing training on NVIDIA supercomputers, providing better image quality and performance across more games and applications.

DLSS 3 With Optical Multi Frame Generation

Boosts performance by using AI to generate more frames. DLSS analyzes sequential frames and motion data from the new Optical Flow Accelerator in GeForce RTX 40 Series GPUs to create additional high-quality frames.

See DLSS 3 in Action in Top Titles

Cyberpunk 2077

Portal with RTX

Microsoft Flight Simulator

Check Out DLSS-Supported Game Engines

DLSS comparison in Fortnite

Unreal Engine (UE)

DLSS 3 is available in Unreal Engine 5 through our official plugin. Unreal Engine developers can benefit from the boosted frame rates and beautiful, sharp images that DLSS creates.

Get Started


DLSS Super Resolution is natively supported for the High-Definition Render Pipeline (HDRP) in Unity 2021.2 and higher. Unity developers can benefit from the performance headroom to maximize ray tracing settings, boost frame rates, and increase output resolution, resulting in beautiful, sharp images that DLSS creates.

Download Unity

Test Experimental Models for DLSS Research

NVIDIA is enabling developers to explore and evaluate experimental AI models for DLSS. Developers can download experimental dynamic-link libraries (DLLs), test how the latest DLSS research enhances their games, and provide feedback for future improvements.

Download the latest DLLs

Stay Up to Date on NVIDIA DLSS News

April 10, 2023

Upcoming Event: Level Up with NVIDIA Nsight Graphics and Optimize Your Game

Supercharging AI Video and AI Inference Performance with NVIDIA L4 GPUs

March 21, 2023

Supercharging AI Video and AI Inference Performance with NVIDIA L4 GPUs

Ultra-Realism Made Accessible with NVIDIA AI and Path Tracing Technologies

March 20, 2023

Ultra-Realism Made Accessible with NVIDIA AI and Path Tracing Technologies

March 10, 2023

Top Path Tracing Sessions at NVIDIA GTC?2023

View all industry news

NVIDIA DLSS Sessions On-Demand

Keep Up with the Latest in NVIDIA Game Development

Get Answers to Frequently Asked Questions

A: DLSS is a deep learning neural network that uses the power of the NVIDIA RTX? Tensor Cores to boost frame rates and generate sharp frames that approach or exceed native rendering.

A: DLSS is powered by NVIDIA RTX Tensor Cores. By tapping into a deep learning neural network, DLSS is able to combine anti-aliasing, feature enhancement, image sharpening, and display scaling, which traditional anti-aliasing solutions cannot. With this approach, DLSS can multiply performance with comparable image quality to full-resolution native rendering.

A: Sign up to be notified as soon as the DLSS 3 SDK is released. To get your game ready for DLSS 3, integrate DLSS 2 and NVIDIA Reflex plugins via NVIDIA Streamline, an open-sourced cross-independent hardware vendor (IHV) solution that simplifies NVIDIA technology integrations. Learn more here.

A: You can access the binary Unreal Engine DLSS plug-in here. You can also get source code via GitHub. Follow the instructions on the UE/GitHub page to link your Epic Games and GitHub accounts to gain access. The plug-in is compatible with UE5 and UE4.26.

A: DLSS super resolution is available for all NVIDIA RTX GPUs. DLSS 3 with Optical Multi Frame Generation is available for GeForce RTX 40 Series GPUs.

A: Yes, NVIDIA Image Scaling (SDK) is an open-source, best-in-class, spatial upscaler and sharpening algorithm that works cross-platform on all GPUs. NVIDIA Image Scaling SDK is a great compliment to NVIDIA DLSS for developers looking for a solution to support non-RTX GPUs. Learn more here.

Ready to start developing with DLSS?

Download DLSS Now