AmusementClub/vs-mlrt

Efficient CPU/GPU ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet, ArtCNN and more!)

49
/ 100
Emerging

This project helps video editors and post-production specialists enhance video quality using advanced machine learning filters within VapourSynth. It takes your raw or low-quality video frames and applies AI-powered upscaling, noise reduction, or interpolation to produce sharper, cleaner, and smoother footage. Anyone working with video restoration, animation upscaling, or general video quality improvement will find this useful.

420 stars.

Use this if you need to apply AI-based video enhancement filters like upscaling (e.g., waifu2x, RealESRGAN), noise reduction (e.g., DPIR), or frame interpolation (e.g., RIFE) in VapourSynth, leveraging your specific GPU hardware (NVIDIA, AMD, Intel) or CPU for optimal performance.

Not ideal if you are looking for a standalone video editing application or a simple one-click solution without using VapourSynth, as this project provides runtime backends for existing VapourSynth ML filters.

video-editing post-production video-upscaling video-restoration animation-enhancement
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

420

Forks

28

Language

C++

License

GPL-3.0

Last pushed

Feb 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmusementClub/vs-mlrt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.