# Lucchetto/SuperImage

Sharpen your low-resolution pictures with the power of AI upscaling

Repository: https://github.com/Lucchetto/SuperImage
Canonical: https://ross.abutalabs.com/products/superimage
Language: Kotlin
License: GPL-3.0
License Family: copyleft
Topics: android, mnn, real-esrgan, super-resolution, upscaling, image-processing, compose
Archived: true
Last push: 2023-11-09T19:26:12+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 93
- inputs: {"age_days": 1309, "days_push": 1028, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1630, forks 109 (observed 2026-08-28T04:05:13.998725+00:00)

## What it is
SuperImage is an Android application that upscales low-resolution images using a Real-ESRGAN neural network running on-device via the MNN deep learning framework. It processes images in tiles on the GPU (requiring Vulkan or OpenCL) and merges them into a high-resolution output.

## Use cases
- upscale low-resolution photos on my phone
- enhance blurry old pictures with AI
- increase image resolution 4x or 16x offline
- sharpen anime or drawing images on Android
- super-resolution without uploading images to a server
- restore quality of compressed images on device

## When to choose
- you want fully on-device AI upscaling with no cloud dependency
- you need a free, open-source Android app for Real-ESRGAN super-resolution
- your device has Vulkan or OpenCL GPU support and Android 7+

## When to avoid
- you need batch processing or transparency support (not yet implemented)
- you need upscaling on desktop or web (not available)
- your device lacks Vulkan/OpenCL GPU support or runs Android below 7

## Facets
- artifact type: application
- maturity: active
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, machine-learning, android-tools, photography
- platform: -
- tags: super-resolution, real-esrgan, upscaling, mnn, jetpack-compose, on-device-ai, android

## Member repositories
- Lucchetto/SuperImage (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:13.998725+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 2026-08-30T03:47:52.394419+00:00, confidence not recorded.
  - readme: https://github.com/Lucchetto/SuperImage (fetched 2026-08-28T04:05:13.998725+00:00, sha e97936652f9b)
- Data as of 2026-08-30T08:39:29.467469+00:00.