NVIDIA DLSS 4 with Multi Frame Generation has change into the fastest-adopted NVIDIA gaming technology ever. Over 250 games and apps use it to make real-time path tracing possible—and upcoming titles for 2026, including PRAGMATA and Resident Evil Requiem, also plan to include the software.Â
At CES 2026, the technology became much more powerful. NVIDIA introduced DLSS 4.5 with a second-generation transformer model for super resolution, and a 6x mode for Multi Frame Generation and Dynamic Multi Frame Generation that routinely shifts the frame generation multiplier in real time to maximise smoothness across games and scenes.
Today, developers can begin using the second-generation transformer model for DLSS Super Resolution to supply superior image quality.
A more powerful DLSS Super Resolution model
DLSS 4 introduced a transformer model architecture with NVIDIA GeForce RTX 50 Series GPUs. That enabled a leap in image quality over our previous convolutional neural network. The second-gen transformer model for DLSS 4.5 Super Resolution uses 5x more compute and is trained on an expanded data set, so it has greater context awareness of each scene and more intelligent use of pixel sampling and motion vectors.Â
This latest model delivers increased temporal stability, superior anti-aliasing, and clearer gameplay in motion. By leveraging the facility of the second-generation transformer, Performance Mode is now comparable to—and may even beat—native image quality, while Ultra Performance has evolved into a really viable mode for 4K gaming.
Developers can get access to DLSS 4.5 Super Resolution through the DLSS Super Resolution Streamline Plugin today. Dynamic Multi Frame Generation and Multi Frame Gen with as much as 6x mode will likely be available through the DLSS Multi Frame Generation Streamline Plugin this spring.
Neural shading made faster
The RTX Neural Shaders SDK was introduced last 12 months with the GeForce RTX 50 Series GPUs. Neural shading represents a paradigm shift for a way developers can use shaders of their graphics pipeline. The SDK lets developers train and deploy tiny neural networks from inside shaders, and construct applications that allow AI to reinforce the gameplay experience. One such application is using AI for texture compression.
The RTX Neural Texture Compression SDK is an application of neural shaders. It uses AI to significantly compress textures greater than traditional methods while maintaining similar image quality. This has resulted in significant performance improvements in the brand new 0.9 version. Block Compression 7 (BC7) encoding has been sped up by 6x, and inference speed has increased by 20% to 40% in comparison with version 0.8. That permits developers to reduce FPS impact when saving as much as 7x system memory.
Developers can start with the most recent RTX Neural Texture Compression SDK today. As well as, RTX Kit update 2026.1 is live with the RTX Neural Shaders SDK—which has received bug fixes—and RTX Character Rendering SDK, which added Vulkan support for RTX Hair.Â
Start with NVIDIA tools for neural shading though the NVIDIA RTX Kit. Â
NVIDIA ACE expands small language model support
NVIDIA ACE is a set of AI technologies—spanning models, developers tools, and on-device inference—that’s designed to assist middleware and game developers construct knowledgeable, actionable, and conversational in-game characters. The NVIDIA Nemotron Nano 9B V2 model is now available through NVIDIA ACE as an In-game Inferencing (IGI) SDK plugin. It simplifies the mixing inside your gaming pipeline and optimizes simultaneous AI inference and graphics processing for accelerated game performance.Â
Developers have the choice to disable intermediate reasoning traces to hurry up response generation at a slight decrease in accuracy for more difficult prompts. This model enables developers to construct enhanced game characters able to real-time reasoning through non-scripted events, dynamic responses based on player inputs, and contextually accurate actions.
Alongside this release, Qwen3-8B support has expanded with 4B and 600M models. This offers developers alternative when balancing speed, quality, and memory usage when integrating these models at runtime.
Test drive the Nemotron Nano 9B V2 at construct.NVIDIA.com, then download the most recent IGI SDK and plugins today to start on game integrations.
NVIDIA Nsight Graphics 2025.5 adds dynamic shader editing, RTX hair support
NVIDIA Nsight Graphics recently released version 2025.5, with a deal with stability and have completeness for the Graphics Capture activity. Graphics Capture provides a brand new foundation of tools and workflows for debugging D3D12 and Vulkan applications.Â
This release introduces dynamic editing of shader code in captured frames, in addition to support for visualization of RTX Hair primitives (LSS hair) within the Ray Tracing Inspector. The GPU Trace Profiler also has quite a few improvements, including a brand new workflow for organizing multiple traces taken in a single session. For more details see the Nsight Graphics 2025.5 release highlight video.
Resources for game developers
See our full list of game developer resources here and follow us to remain up-to-date with the most recent NVIDIA Game development news:Â
