QualityScaler

Windows AI app for image and video upscaling, denoising, and stop-and-resume video processing

Open Source Alternative to
Repository activity
  • Stars3.1k
  • Forks253
  • Open Issues42
License

MIT

Languages
  • Python
Get it:Website
QualityScaler screenshot

About QualityScaler

QualityScaler is a Windows app that enhances, upscales, and denoises photos and videos with AI. Everything runs on your own PC with local models, so no internet connection is needed and your files never leave your machine.

It upscales both images and video, with automatic tiling to work within GPU VRAM limits, multi-GPU support, resize-before-upscale, and interpolation to blend the original with the upscaled result. Video jobs can be stopped and resumed. It reads common image formats such as JPG, PNG, TIFF, BMP, WebP, and HEIC, and video formats including MP4, MKV, AVI, MOV, and WebM.

QualityScaler targets Windows 10 and 11 and needs a DirectX 12 compatible GPU with at least 4 GB of VRAM.

Key features

  • AI upscaling for both images and video
  • Automatic tiling to fit GPU VRAM limits
  • Resize before upscaling
  • Interpolation between original and upscaled output
  • Stop and resume video jobs

Details

On GitHub since
2022
Platforms
Windows
Deployment
Offline-first
GPU
DirectX 12, 4 GB VRAM min
Processing
Local AI models
Media
Images and video