Likely7/Veyra-NRVideo

Bring PS5 GTA6 to 120FPS with DLSS 5. An advanced Windows video player and capture enhancement tool featuring real-time preview for videos, images, and capture card sources. Combine AI-powered Super Resolution, DLSS5 image enhancement, and Frame Generation to deliver a next-generation visual experience.

What it solves

Veyra is a real-time GPU-accelerated video enhancement tool for Windows. It solves the problem of low-quality video sources—such as local files, capture cards, and game streams from PS5, Xbox, or PC—by applying a pipeline of super-resolution, denoising, and frame generation to improve visual fidelity in real-time.

How it works

The software uses a DirectX 12 backend to process video frames through a customizable enhancement graph. Users can choose from multiple noise reduction (NR) runtimes (including NVIDIA and AMD options) and apply super-resolution (SR) and RTX Video HDR. It features two primary modes of operation:

  • List Mode: A streamlined interface for enabling and configuring up to four layers of noise reduction and other effects.
  • Node Mode: A visual executable chain editor where users can build complex processing paths by connecting input and output ports for NR, colour, and SR nodes.

Who it’s for

It is designed for gamers, streamers, and video enthusiasts who want to upscale and clean up live video feeds from consoles or PCs, as well as those who need a professional-grade offline export workflow for enhanced video.

Highlights

  • Multi-Source Support: Compatible with local files, screen capture, capture cards, and remote streaming (Moonlight/Sunshine, PS5 Remote Play, and experimental Xbox support).
  • Layered Noise Reduction: Supports up to four independent NR layers with adjustable strength and internal resolution.
  • Frame Generation: Integrated FG backends to increase perceived smoothness of the video output.
  • Advanced Colour Grading: Includes curves, mixers, wheels, LUTs, and professional colour presets.
  • Flexible Export: An ordered queue for offline exporting to MP4/MKV with support for multiple audio and subtitle tracks.

Related

  • Project
    Merserk/dlss5-visual-enhancer

    A portable Windows app for NVIDIA RTX GPUs that uses DLSS 5 Neural Rendering and other AI tools to upscale and enhance images, videos, and live streams.

  • Project
    perseval-BLR/NeuralScreen

    NeuralScreen is a Windows‑only overlay that runs NVIDIA’s DLSS 5 neural renderer on the whole desktop (or a single window) in real time, optionally adding DLSS‑G frame generation. It works with RTX GPUs, offers hot‑key control, per‑window mode, recording, and a configurable UI.

  • Project
    VisionDepth/VisionDepth3D

    VisionDepth 3D is a Windows desktop app that converts 2‑D images or videos into stereoscopic 3‑D using AI depth models, depth‑map blending, RIFE frame‑interpolation, and AI super‑resolution. It offers a free tier (limited length, 1080p, watermarked) and a one‑time $59.99 Pro tier (no limits, 4K+, batch processing, advanced controls). Installation is via an Itch.io “Setup Hub” that provides CUDA (NVIDIA) or DirectML (AMD/Intel) builds. The software is proprietary, but the AI models it downloads are open‑source under their own licenses.

  • Project
    SharpAI/DeepCamera

    An open-source AI camera platform that enables local deployment of VLM scene analysis and object detection skills with autonomous, hardware-aware installation.

  • Project
    NVIDIA-AI-Blueprints/video-search-and-summarization

    The NVIDIA AI Blueprint for Video Search and Summarization (VSS) is a reference architecture that combines vision‑language models, large language models, and NVIDIA NIM micro‑services to enable GPU‑accelerated agents for natural‑language video search, long‑video summarization, visual Q&A, and real‑time alert verification. It provides micro‑services for real‑time video intelligence, downstream analytics, and an orchestrating Python agent, plus a Next.js UI, Docker/Helm deployment scripts, and extensive tooling. Targeted at video analysts and GenAI engineers, it requires NVIDIA AI Enterprise licensing and supported GPUs.