AI SDKs and Models for Your RTX PC Application
Add cutting-edge AI features for your RTX PC applications with NVIDIA SDKs and pretrained models.
Build With NVIDIA AI SDKs
NVIDIA DLSS: Improve Image Quality and Multiply Graphics Performance
Use NVIDIA DLSS, a neural graphics technology that multiplies performance using AI, to create entirely new frames, display higher resolution through image reconstruction, and improve the image quality of intensive ray-traced content—all while delivering best-in-class image quality and responsiveness.
NVIDIA OptiX: Advanced AI Ray Tracing Algorithms on the GPU
Use NVIDIA OptiX™ Ray Tracing Engine, an application framework for achieving optimal ray-tracing performance on the GPU. It provides a simple, recursive, and flexible pipeline for accelerating ray-tracing algorithms, including an advanced AI denoiser. Bring the power of NVIDIA GPUs to ray-tracing applications with programmable intersection, ray generation, and shading.
NVIDIA RTX Kit: Render Photo-Realistic Assets
Use NVIDIA RTX™ Kit, a suite of neural rendering technologies to render assets with AI, better organize geometry for improved path tracing performance, and tools to create assets with photo-realistic visuals.
NVIDIA ACE: Bring Digital Humans to Life
Use NVIDIA ACE - a suite of digital human technologies for bringing digital assistants and game characters to life with generative AI.
NVIDIA AI for Media: Improve Real-Time Audio and Video for modern media workflows
NVIDIA AI for Media brings real-time AI for live video pipelines, localization, content enhancement and synthetic media detection. Designed for live production and post-production workflows, it supports deployment on premises, in the cloud and across modern IP-based media infrastructure.
RTX Video: Improve Streamed Video Quality on Browsers, Creative, and Media Playback Apps
Use NVIDIA RTX Video with AI-enhanced RTX Video Super Resolution and RTX Video HDR effects for creative and media playback apps to improve sharpness, clarity, and the automatic conversion of SDR video to HDR.
Video Codec SDK: Accelerate Video Encode and Decode
Use Video Codec SDK, a comprehensive set of APIs including high-performance tools, samples, and documentation for hardware-accelerated video encode and decode on NVIDIA GPUs, for several popular codecs.
Optical Flow SDK: Track True Object Motion on Videos
Use NVIDIA Optical Flow SDK, which taps into the latest hardware capabilities dedicated to computing the relative motion of pixels between images. The hardware uses sophisticated algorithms to yield highly accurate flow vectors, ideal for handling frame-to-frame intensity variations and tracking true object motion.
Example Workflows Accelerated With NVIDIA AI on RTX PCs
NVIDIA ACE (2:24)
NVIDIA ChatRTX (0:53)
NVIDIA and Blackmagic Design Showcase Enhanced AI Features of NVIDIA RTX (1:26)
GPU-Acceleration Benefits in Adobe Premiere Pro With NVIDIA (1:20)
NVIDIA GET3D: AI Model to Populate Virtual Worlds With 3D Objects and Characters (0:35)
Instantly Create Expressive Facial Animation With NVIDIA Audio2Face (0:45)
Accelerating AI in Photoshop Neural Filters (3:05)
NVIDIA RTX Accelerates AI Super Resolution in Adobe Photoshop (1:39)
Power Your App with State-of-the-Art AI Models for Every Task
Power your application with thousands of pre-trained models that exist in the open-source community, all of which are accelerated on RTX today. Get started today with highly accurate models that span diverse use cases and domains.
Language Models
Language models facilitate application development for natural language downstream tasks like text generation, summarization, chatbots, question answering, translation, and more. These models use the transformer architecture to achieve high accuracy across a wide range of complexities in each task type.
Image Generation Models
NVIDIA is at the forefront of image generation, partnering with popular model developers like Black Forest Labs and Stability.ai.
Explore Image Generation Models
Computer Vision Models
With computer vision, devices can understand the world through images and videos. Computer vision models can be used for image classification, object detection, and tracking, object recognition, semantic segmentation, and instance segmentation.
Explore Computer Vision Models
Speech Models
Speech models deal with recognizing and transcribing audio into text or generating speech from text. It includes text-to-speech (TTS) and automatic speech recognition (ASR) models.
Explore Speech Models
