AI super-resolution and frame interpolation for images/videos
Waifu2x-Extension-GUI is a Windows desktop application that upscales images, GIFs, and videos and performs video frame interpolation using multiple AI engines such as Waifu2x, Real-ESRGAN, Real-CUGAN, Anime4K, and RIFE.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Android app with multi-engine NCNN super-resolution and interpolation; choose when you need on-device mobile processing instead of a Windows desktop tool.
An Android application for super-resolution & interpolation. Contains RealSR-NCNN, SRMD-NCNN, RealCUGAN-NCNN, Real-ESRGAN-NCNN, Waifu2x-NCNN, Anime4kcpp, nearest, bilinear, bicubic, AVIR...
VapourSynth ML runtime with built-in support for several SR and interpolation models; choose when you need scriptable, GPU-accelerated video processing in VapourSynth.
Efficient CPU/GPU ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet, ArtCNN and more!)
Dockerized VapourSynth pipeline with TensorRT-accelerated SR and interpolation models; choose for reproducible scripted video processing on NVIDIA GPUs.
Using VapourSynth with super resolution and interpolation models and speeding them up with TensorRT.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Image-only AI upscaler GUI; choose if you need only still-image enlargement and prefer a simpler light-weight tool.
AI超分辨率工具
Older macOS GUI for waifu2x and other image enlargers; choose when you are on a Mac and need only still-image upscaling.
The waifu2x & Other image-enlargers on Mac
Real-time mpv plugin for anime upscaling during playback; choose for live viewing rather than producing saved upscaled files.
Real-time anime upscaling to 4K in mpv with lightweight super-resolution models
Legacy AviSynth filter implementing old SR neural networks; choose only for scripted AviSynth video workflows.
An AviSynth+ implementation of some Super-Resolution Convolutional Neural Networks.
Browser/WASM implementation for anime-image super-resolution; choose when you need client-side web upscaling without a backend.
Super-resolution processing for anime images based on WASM; 基于WASM的动漫图片超分辨率处理
Specialized manga-page upscaling tool; choose when your input is manga scans instead of mixed images/videos.
Upscale manga with AI models
Research-only diffusion video super-resolution framework; choose only for evaluating a state-of-the-art streaming VSR model, not an all-in-one user tool.
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.
Legacy TensorFlow collection of SR architecture implementations; choose only for academic reimplementation or benchmarking with old models.
A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.
Classic EDSR single-image super-resolution model code; choose if you specifically need that architecture in PyTorch.
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
These projects were analysed and named Waifu2x-Extension-GUI among their alternatives. The relationship is not symmetric — how Waifu2x-Extension-GUI rates them is a separate judgement, made when Waifu2x-Extension-GUI is analysed in its own right.
calls Waifu2x-Extension-GUI “Choose when you want an actively maintained Windows GUI covering video/image/GIF with a wider set of upscaling and interpolation backends.”
A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.
calls Waifu2x-Extension-GUI “A GUI app for video/image upscaling and frame interpolation; choose for desktop use instead of code integration.”
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.