waifu2x (nunif)

Health v2 · maintenance only

Flags: prerelease_only

Adoption not part of the score

3418 stars · 282 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

application · maturity maintenance

image-processing machine-learning deep-learning cli gui image-processing machine-learning deep-learning graphics windows cli super-resolution anime-art upscaling noise-reduction cnn torch7 pytorch waifu2x nunif anime linux macos gpu web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nagadomi/nunif")