# nihui/waifu2x-ncnn-vulkan

waifu2x converter ncnn version, runs fast on intel / amd / nvidia / apple-silicon GPU with vulkan

Repository: https://github.com/nihui/waifu2x-ncnn-vulkan
Canonical: https://ross.abutalabs.com/products/waifu2x-ncnn-vulkan
Language: C++
License: MIT
License Family: permissive
Topics: waifu2x, ncnn, vulkan, gpu, amd, nvidia, intel, windows, linux, macos
Last push: 2026-04-13T16:04:51+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 77, release rhythm 23, longevity 100
- inputs: {"age_days": 2709, "days_push": 142, "days_rel": 352, "gap_med": 134, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3456, forks 240 (observed 2026-08-28T04:08:05.500303+00:00)

## What it is
A portable command-line tool implementing the waifu2x anime-style image upscaler and denoiser using the ncnn inference framework with the Vulkan API. It runs fast on Intel, AMD, NVIDIA, and Apple Silicon GPUs without requiring CUDA or other runtime dependencies.

## Use cases
- upscale anime images 2x with waifu2x
- denoise noisy artwork before upscaling
- batch upscale a folder of images on GPU
- run waifu2x without installing CUDA
- upscale images on Apple Silicon or AMD GPUs
- convert jpg/png/webp to larger lossless png output

## When to choose
- You need fast GPU-accelerated waifu2x upscaling across NVIDIA, AMD, Intel, or Apple Silicon GPUs
- You want a portable binary with no CUDA or Python dependencies
- You need batch processing of image directories from the command line

## When to avoid
- You need real-time upscaling in a GUI application
- Your GPU lacks Vulkan support or has outdated drivers
- You need photo-realistic (non-anime) super-resolution models

## Facets
- artifact type: cli-tool
- maturity: active
- function: image-processing, machine-learning, cli
- domain: image-processing, computer-vision, graphics
- platform: windows, cli, cross-platform
- tags: waifu2x, ncnn, vulkan, upscaling, super-resolution, denoise, anime-images, linux, macos, gpu

## Member repositories
- nihui/waifu2x-ncnn-vulkan (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.500303+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 2026-08-29T18:37:30.295413+00:00, confidence not recorded.
  - readme: https://github.com/nihui/waifu2x-ncnn-vulkan (fetched 2026-08-28T04:08:05.500303+00:00, sha 98b579c42040)
- Data as of 2026-08-30T08:39:29.467469+00:00.