# n00mkrad/cupscale

Image Upscaling GUI based on ESRGAN

Repository: https://github.com/n00mkrad/cupscale
Canonical: https://ross.abutalabs.com/products/cupscale
Language: C#
License: MIT
License Family: permissive
Last push: 2022-09-19T18:15:03+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2189, "days_push": 1444, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2341, forks 141 (observed 2026-08-28T04:06:39.136730+00:00)

## What it is
Cupscale is a Windows GUI application for AI-based image upscaling built around ESRGAN and Real-ESRGAN models. It supports CUDA, Vulkan/NCNN, and CPU backends with features like model chaining, batch upscaling, and automatic image tiling.

## Use cases
- upscale low-resolution images with AI
- run ESRGAN models without command line
- batch upscale a folder of images
- upscale images on an AMD or Intel GPU
- create before/after comparison animations of upscaled images
- avoid out-of-memory errors when upscaling large images

## When to choose
- you want a simple GUI for ESRGAN/Real-ESRGAN upscaling on Windows
- you need batch upscaling or model chaining
- you have a non-NVIDIA GPU and need Vulkan/NCNN support

## When to avoid
- you need a command-line or headless upscaling pipeline
- you need Linux/macOS native support
- you need actively developed features - the project has not released since 2022

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, gui
- domain: image-processing, machine-learning, media
- platform: windows, cross-platform
- tags: esrgan, upscaling, super-resolution, ncnn, vulkan, cuda, real-esrgan, desktop

## Member repositories
- n00mkrad/cupscale (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:39.136730+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 2026-08-30T02:37:23.084224+00:00, confidence not recorded.
  - readme: https://github.com/n00mkrad/cupscale (fetched 2026-08-28T04:06:39.136730+00:00, sha 0aa38ba715a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.