# Kiteretsu77/APISR

APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)

Repository: https://github.com/Kiteretsu77/APISR
Canonical: https://ross.abutalabs.com/products/apisr
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2025-10-16T00:57:56+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 47, release rhythm 8, longevity 65
- inputs: {"age_days": 914, "days_push": 322, "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 1135, forks 70 (observed 2026-08-28T04:03:43.565324+00:00)

## What it is
APISR is a deep-learning based super-resolution tool that restores and enhances low-quality, low-resolution anime images and videos using techniques inspired by anime production pipelines. It provides pretrained upscaler weights (2x, 4x), a Gradio demo, and training code, published at CVPR 2024.

## Use cases
- upscale low-resolution anime images
- enhance degraded anime video quality
- restore real-world degraded anime screenshots
- super-resolution for 2x and 4x anime upscaling
- train a custom anime super-resolution model
- run anime upscaling in a Gradio web demo

## When to choose
- you need to upscale or restore anime images or video frames
- you want state-of-the-art anime-specific super-resolution rather than generic photo upscalers
- you need pretrained 2x/4x weights or want to train your own model

## When to avoid
- you need to upscale real-world photographs rather than anime content
- you need a lightweight CPU-only tool without GPU resources
- you need a polished end-user application rather than a research codebase

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning, video-processing
- domain: image-processing, computer-vision, machine-learning, media
- platform: python, cross-platform
- tags: super-resolution, anime-upscaling, image-restoration, video-upscaling, cvpr-2024, gradio-demo, gpu

## Member repositories
- Kiteretsu77/APISR (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:43.565324+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 2026-08-30T06:36:34.794552+00:00, confidence not recorded.
  - readme: https://github.com/Kiteretsu77/APISR (fetched 2026-08-28T04:03:43.565324+00:00, sha fd53e7b65f2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.