NVIDIA DLSS is a suite of neural rendering technologies powered by NVIDIA RTX™ Tensor Cores that boosts frame rates while delivering crisp, high-quality images that rival native resolution. DLSS 4 introduced Multi Frame Generation (MFG) and a transformer model for high quality super resolution. DLSS 4.5 introduces the second-generation transformer model for Super Resolution, and Dynamic Multi Frame Generation

• DLSS Multi Frame Generation boosts frame rates by using AI to generate up to five frames per rendered frame powered by NVIDIA GeForce RTX 50 Series and RTX PRO Blackwell Generation GPUs with fifth-generation Tensor Cores.

• DLSS Dynamic Multi Frame Generation Dynamically adjusts the frame generation multiplier to maximize smoothness across different games and scenes.

• DLSS Frame Generation boosts performance by using AI to generate frames while maintaining great responsiveness with NVIDIA Reflex.

• DLSS Ray Reconstruction enhances image quality by using AI to generate additional pixels for intensive ray-traced scenes. DLSS replaces hand-tuned denoisers with an NVIDIA supercomputer-trained AI network that generates higherquality pixels between sampled rays.

• DLSS Super Resolution boosts performance by using AI to output higher-resolution frames from a lower-resolution input. DLSS samples multiple lower-resolution images and uses motion data and feedback from prior frames to construct highquality images. A new second-generation Transformer AI model further improves stability, anti-aliasing, and visual clarity.

• Deep Learning Anti-Aliasing provides higher image quality with an AI-based antialiasing technique. DLAA uses the same Super Resolution technology developed for DLSS, constructing a more realistic, high-quality image at native resolution.

DLSS Super Resolution, Ray Reconstruction, and DLAA use cutting-edge transformer AI models trained by NVIDIA’s supercomputers for the best image quality