# waifu2x (nunif)

Misc; latest version of waifu2x;  2D video to stereo 3D video conversion

Repository: https://github.com/nagadomi/nunif
Canonical: https://ross.abutalabs.com/products/waifu2x-nunif
Language: Python
License: MIT
License Family: permissive
Topics: super-resolution, vr, waifu2x
Last push: 2026-08-22T05:32:23+00:00
Link (homepage): http://waifu2x.udp.jp/ 

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 39, longevity 100
- inputs: {"age_days": 2577, "days_push": 11, "days_rel": 196, "gap_med": 207.0, "n_releases_24m": 3}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3418, forks 282 (observed 2026-08-28T04:08:03.778456+00:00)

## What it is
waifu2x is an image super-resolution and noise-reduction tool for anime-style art (and photos) using deep convolutional neural networks, originally written in Lua/Torch7. Development has moved to the nunif repository (PyTorch), with a hosted web demo and in-browser version also available.

## Use cases
- upscale anime artwork without losing quality
- reduce jpeg noise in manga scans
- enlarge low-resolution illustrations 2x or 4x
- super-resolve anime-style images with a neural network
- denoise and upscale photos
- batch upscale images from the command line

## When to choose
- you need high-quality upscaling of anime/illustration art
- you want a proven, widely-used super-resolution tool with a web demo
- you have an NVIDIA GPU and want CLI or self-hosted processing

## When to avoid
- you need active development on the original Lua repo - it has moved to nunif
- you have no GPU and want fast local processing (consider waifu2x-ncnn-vulkan instead)
- you need upscaling of general photographic content with state-of-the-art models

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, cli, gui
- domain: image-processing, machine-learning, deep-learning, graphics
- platform: windows, cli
- tags: super-resolution, anime-art, upscaling, noise-reduction, cnn, torch7, pytorch, waifu2x, nunif, anime, linux, macos, gpu, web-server

## Member repositories
- nagadomi/nunif (main) score 78
- nagadomi/waifu2x (mirror) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:03.778456+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 2026-08-29T16:54:25.505387+00:00, confidence not recorded.
  - readme: https://github.com/nagadomi/nunif (fetched 2026-08-28T04:08:03.778456+00:00, sha c58e486a4360)
  - homepage: http://waifu2x.udp.jp/  (fetched 2026-08-29T07:50:59.413565+00:00, sha be50efeef780)
- Data as of 2026-08-30T08:39:29.467469+00:00.