# Djdefrag/QualityScaler

QualityScaler - image/video AI upscaler app

Repository: https://github.com/Djdefrag/QualityScaler
Canonical: https://ross.abutalabs.com/products/qualityscaler
Language: Python
License: MIT
License Family: permissive
Topics: python, amd, intel, nvidia, directx-12, windows, compression-artifact-reduction, deep-learning, gui-application, noise-reduction, opencv, python3, pytorch, super-resolution, anime, manga, video, video-processing, onnx, onnxruntime
Last push: 2026-08-26T16:14:26+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 87, longevity 100
- inputs: {"age_days": 1613, "days_push": 7, "days_rel": 7, "gap_med": 51.5, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3138, forks 253 (observed 2026-08-28T04:07:45.755222+00:00)

## What it is
QualityScaler is a Windows GUI application that uses AI deep-learning models to upscale, enhance, and de-noise images and videos. It is written entirely in Python using PyTorch, ONNX Runtime with DirectML, and OpenCV, supporting AMD, Intel, and NVIDIA GPUs.

## Use cases
- upscale low-resolution photos with AI
- enhance and denoise old videos
- remove compression artifacts from images
- upscale anime and manga images
- AI super-resolution on Windows without NVIDIA-specific setup
- sharpen blurry video footage

## When to choose
- you need a ready-to-use Windows GUI for AI image/video upscaling
- you have an AMD or Intel GPU since it uses DirectML rather than CUDA-only
- you want to upscale anime or manga artwork
- you want denoising and artifact reduction alongside upscaling

## When to avoid
- you need a Linux or macOS upscaler - it is Windows-only
- you need a command-line or batch pipeline tool rather than a GUI app
- you need Real-ESRGAN specifically - the author's RealScaler targets that
- you want to run on headless servers or integrate upscaling into your own code

## Facets
- artifact type: application
- maturity: active
- function: image-processing, video-processing, machine-learning, deep-learning, gui
- domain: image-processing, machine-learning, media
- platform: windows, python
- tags: super-resolution, upscaler, denoising, onnxruntime, directml, anime-upscaling, bsrgan, realesrgan, pytorch, desktop-app, video, gpu

## Member repositories
- Djdefrag/QualityScaler (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:45.755222+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:26:03.532351+00:00, confidence not recorded.
  - readme: https://github.com/Djdefrag/QualityScaler (fetched 2026-08-28T04:07:45.755222+00:00, sha 5e296a0bee54)
- Data as of 2026-08-30T08:39:29.467469+00:00.