# k4yt3x/video2x

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

Repository: https://github.com/k4yt3x/video2x
Canonical: https://ross.abutalabs.com/products/video2x
Homepage: https://docs.video2x.org
Language: C++
License: AGPL-3.0
License Family: copyleft
Topics: machine-learning, anime4k, vulkan, realesrgan, neural-networks, super-resoluion, upscale-video, rife, frame-interpolation, realcugan
Last push: 2026-03-07T15:39:42+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 71, release rhythm 40, longevity 100
- inputs: {"age_days": 3112, "days_push": 179, "days_rel": 586, "gap_med": 7.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21263, forks 1839 (observed 2026-08-28T04:11:31.497333+00:00)

## What it is
Video2X is a machine learning-based video super-resolution and frame interpolation framework written in C/C++. It upscales videos and images using models like Anime4K, Real-ESRGAN, and Real-CUGAN, and interpolates frames with RIFE, running on Vulkan-capable GPUs.

## Use cases
- upscale low-resolution videos to higher resolution
- increase video frame rate with frame interpolation
- enhance anime video quality
- upscale images with Real-ESRGAN
- restore old or blurry video footage

## When to choose
- you need GPU-accelerated video upscaling with state-of-the-art models
- you want a GUI tool on Windows or a CLI on Linux
- you work with anime content and want Anime4K or Real-CUGAN support

## When to avoid
- your GPU does not support Vulkan or your CPU lacks AVX2
- you need macOS support
- you need a lightweight non-ML upscaler

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, video-processing, image-processing, gpu-computing
- domain: machine-learning, image-processing, media
- platform: windows, cpp
- tags: video-upscaling, super-resolution, frame-interpolation, anime4k, realesrgan, rife, vulkan, ncnn, video, linux, gpu

## Member repositories
- k4yt3x/video2x (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.497333+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 2026-08-29T16:58:26.878039+00:00, confidence not recorded.
  - readme: https://github.com/k4yt3x/video2x (fetched 2026-08-28T04:11:31.497333+00:00, sha 0d90042ba4e7)
  - homepage: https://docs.video2x.org (fetched 2026-08-29T07:56:51.154410+00:00, sha 93ab4497721b)
- Data as of 2026-08-30T08:39:29.467469+00:00.