Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, SRMD, RealSR, Anime4K, RIFE, CAIN, DAIN and ACNet.

Overview

Waifu2x-Extension-GUI

Photo/Video/GIF enlargement and Video frame interpolation using machine learning

Supports AMD / Nvidia / Intel GPU

📜 中文版说明文档 | Official telegram channel

💾 Download Latest Stable Build (Windows x64)

Download Latest portable package for Windows x64 PCs with Intel/AMD/Nvidia GPUs.

Download Latest Build: https://github.com/AaronFeng753/Waifu2x-Extension-GUI/releases/latest

Get Premium version on Patreon: https://patreon.com/aaronfeng

📝 Full change log

Supported Languages: English, 简体中文, 繁體中文.

🌟 Download Beta Build (Windows x64)

The beta build has a faster update cycle than the stable build, which allows you to experience the latest features of the software in advance.

Beta builds are more unstable than the stable builds because the beta builds have not been fully tested before release.

Download the beta build at the releases page: https://github.com/AaronFeng753/Waifu2x-Extension-GUI/releases

What is Waifu2x-Extension-GUI?

Image & GIF & Video Super-Resolution and Video Frame Interpolation using Deep Convolutional Neural Networks.

Key features:

  • 📺 Multimedia support: Supports processing Image & GIF&APNG & Video at the same time.

  • 😍 Full image style support: Multiple built-in algorithms, 2D anime, or your daily photos & videos, this software can handle all of them.

  • 🎞 Video frame interpolation: Automatically use AI to interpolate frames after enlarge the video.

  • Video Frame Analysis: Analyze video frames to Improve video Quality and Speed Up video processing.

  • Great compatibility: Multiple built-in engines, compatible with almost all modern Windows PCs.

  • 📊 Flexible multi-thread setting: You can adjust the number of threads freely while providing a complete set of settings for each engine, Take advantage of all the capabilities of your PC.
  • 🚀 🚀 🚀 Multi-GPU support: Multi-GPU support for ALL built-in engines.
  • 🛠 Numerous customizable settings: You can automate your workflow by adjusting the many customizable settings in the software.
  • 🤖 Smart settings: This software can automatically adjust some software settings based on your PC hardware information and the information of the files you want to process.
  • 😉 Easy-to-use graphical user interface.
  • 📨 Continual maintenance and updates.
Built-in super-resolution algorithms:
Waifu2x / SRMD / RealSR / Anime4K / ACNet

Built-in super-resolution engines:
Waifu2x-caffe / Waifu2x-converter / Waifu2x-ncnn-vulkan
SRMD-ncnn-vulkan / RealSR-ncnn-vulkan / Anime4KCPP / SRMD-CUDA

Built-in Video frame interpolation algorithms:
RIFE / CAIN / DAIN

Built-in Video frame interpolation engines:
rife-ncnn-vulkan / cain-ncnn-vulkan / dain-ncnn-vulkan

Already been tested on the AMD RX 550, NVIDIA GeForce RTX 3060 and Intel UHD 620.

mainwindow

Engine_Settings

Additional_Settings

Samples 👀

Comparison(3D Real-life)(Using RealSR-NCNN-Vulkan Engine)

Photo by Jonatan Pie on Unsplash

Comparison

Comparison(2D Anime)(Using Waifu2x-NCNN-Vulkan Engine)

Comparison

Original 2D Anime Image 480x300 (.jpg 93.2 KB):

Original Imgae

After 8x magnification, level 3 denoise and compress 3840x2400 (.jpg 525 KB):

(Using Waifu2x-NCNN-Vulkan Engine)

Scaled Imgae

Original GIF 500 x 372 (493 KB):

Original GIF

After 2x magnification, level 2 denoise and gif optimize 1000 x 744 (3.77 MB):

(Using Waifu2x-NCNN-Vulkan Engine)

Scaled GIF

Github doesn't support online video playback, please check link below:

My Youtube channel: https://www.youtube.com/channel/UCUIdGDuH32mTAVL6_6uQdXQ

Video : https://github.com/AaronFeng753/Waifu2x-Extension-GUI/tree/master/Samples/video

Donate (推荐使用 支付宝 或者 微信)

Patreon donate button

PayPal

除了扫码捐赠现金, 您也可以每天打开支付宝首页搜“682796694”领红包并使用, 我也可以获得收入.

donate_new

如果捐赠二维码图片无法正常加载,请打开此链接查看或者合法的连接国际网络后刷新页面, 当然您也可以按照这个教程来尝试修复github图片加载的问题.

📄 License

Waifu2x-Extension-GUI is free for PERSONAL USE ONLY.

If you wish to use Waifu2x-Extension-GUI commercially, please purchase the Premium version from:

https://www.patreon.com/aaronfeng

Privacy policy 🙈 🙉 🙊

We respect your privacy, so the following is the privacy policy of this software:

1. This software won't upload anything to the internet, so we won't collect any data from you, we don't even have a server.

2. This software will only connect to the internet when checking for new updates and update the QRCode on the Donate tab, which
will download two .ini files and two .jpg files from GitHub and Gitee. (Gitee is a copycat version of GitHub in The
People's Republic of China, you can disable downloading anything from Gitee by enabling [Ban Gitee] in [Additional settings])

In conclusion, we won't collect any data from you.

💝 Credits 💝 :

Issues
  • Copy Audio Stream/Copy Video Stream settings ignored

    Copy Audio Stream/Copy Video Stream settings ignored

    Video and audio is being converted despite the options to copy the audio and video streams being ticked.

    The previous version worked fine, and I've had to go back to using that one for the time being.

    enhancement fixed Not a bug 
    opened by Bostonjunk 27
  • Selecting sleep when done no longer works

    Selecting sleep when done no longer works

    Selecting sleep when done no longer works. I get a box asking whether I want to sleep immediately, and it goes no further. I want to leave a project running and have the computer sleep when done automatically This no longer works..

    bug fixed 
    opened by 4-testing 25
  • Frames are being skipped

    Frames are being skipped

    Whenever i try upscaling a gif it makes some kind of weird double frames and it looks like its skipping some frames in the upscaled one, it isn't like the original, not sure what's the problem.

    bug fixed 
    opened by GamerzHell9137 25
  • [Feature request] Add Real-ESRGAN to the list of upscaler

    [Feature request] Add Real-ESRGAN to the list of upscaler

    Is your feature request related to a problem? Please describe. No, this is merely a request to add an upscaler.

    Describe the solution you'd like https://github.com/xinntao/Real-ESRGAN In there, is a ncnn version of Real-ESRGAN, which in structure is very similar to RealSR, but has superior video quality. it would be really cool to have it in your software!

    Describe alternatives you've considered Theres no alternative, just a request.

    Additional context I have no further context.

    fixed Feature request 
    opened by Tsubajashi 21
  • v0.461,视频质量劣化(前期图像处理)问题

    v0.461,视频质量劣化(前期图像处理)问题

    我测试一段视频,对比v0.37有着一眼能看出的劣化,囧 我一开始以为是视频编码器问题

    但是我重新折腾几次发现 v0.461这个,在处理视频的时候,拆分图像上,就已经和v0.37有着画质差别(比0.37更糊) 然后,用这个已经劣化的图片再放大,就是糊上加糊

    我已经把v0.461和v0.37的最终视频,拆分图像,以及放大图像,原始视频,都单独复制出来并上传网盘了 其中 160,眼镜的脸,和肌肉那块 Snipaste_2020-02-22_22-03-30

    232,妹子的边缘 Snipaste_2020-02-22_22-04-32

    链接:https://pan.baidu.com/s/10kf3j7e2KpJGJpAW0tw9yg 提取码:cgow

    请查收

    软件设置参数 自定义分辨率3840x2160 保持宽高比 视频,降噪3 视频,内部线程3

    压缩JPG和保存为JPG都未勾选

    引擎默认,块大小200默认

    硬件参数 8700k oc4.69 64g ram 1080TI

    烦请排查问题所在 如果需要,我也可以提供更详细信息

    opened by slimekingwin8cn 19
  • Converted images are black

    Converted images are black

    I'm using version 0.52 beta, my video card is an RX570. When using Waifu2x-ncn-vulkan engine the result is black images (see screenshot). This did not happen in any previous version. To get around this I'm having to use the waifu2x-converter engine, which is much slower. image

    fixed 
    opened by flaviojcojr 17
  • [BUG Report] [Patch available] Program crashes when trying to upscale PSD

    [BUG Report] [Patch available] Program crashes when trying to upscale PSD

    Edit: (@AaronFeng753)

    [Patch] Quick FIX for PSD processing

    https://www.patreon.com/posts/53351638

    OR just download the v3.70.11-BETA version:

    https://www.patreon.com/posts/v3-70-11-beta-53564792


    Software Version Latest Stable

    Describe the bug When attempting to upscale a PSD, the program reaches the stage of extracting layer information before crashing. A folder is generated in the output directory with an empty results.txt file.

    How to Reproduce the bug Steps to reproduce the bug:

    1. Make sure that the GIMP .exe path and scripts folder path are correctly set before running, otherwise the program will display an error message before getting to the point where the crash occurs.
    2. Load the provided test file into the processing queue.
    3. Hit start and wait.

    Expected behavior The program should go through the steps of processing the PSD instead of crashing.

    Screenshots Video recording of an attempt to upscale the provided test file.

    https://user-images.githubusercontent.com/24994538/124498455-e2d9c200-ddab-11eb-9110-7a979be1660b.mp4

    Files you were trying to process when encountered the BUG

    test.zip

    Desktop (please complete the following information):

    • OS: Windows 10 20H2
    • GPU Model: AMD Radeon 5700 XT
    • CPU Model: AMD Ryzen 7 3700X
    • Amount of RAM: 32GB
    • Amount of VRAM: 8GB
    • Amount of Storage: 930GB (569GB free)
    bug fixed 
    opened by missing-q 16
  • Program freezes the first time it opens during compatibility test

    Program freezes the first time it opens during compatibility test

    • Program freezes the first time it opens during compatibility test;
    • Even after several minutes the other commands remain grayed out;
    • Closing the program and reopening solves the problem.

    image

    My current Specs Intel Core i5-9400F 16GB DIMM DDR4 clocked @ 2400 MHz GeForce GTX 1660 SUPER GAMING OC 6G

    fixed 
    opened by flaviojcojr 14
  • Resume progress when frame cache in the RAM is lost

    Resume progress when frame cache in the RAM is lost

    If using the RAM cache everything works fine. But if you stop processing before the video upscaling is complete, detach or restart pc, and then continue processing, the program will crash. It can be fixed by changing isSplitComplete and isScaleComplete in the video config to false, but then ffpmpeg runs in the background (and uses 20% cpu at 100% normally) without splitting any frames. If press stop, ffpmeg wont stop, and the only way is to kill the process. After killing ffmpeg, in log

    Stream #0:0 -> #0:0 (hevc (native) -> mjpeg (native))
    Press [q] to stop, [?] for help
    [swscaler @ 00000292f3ac2c00] deprecated pixel format used, make sure you did set range correctly
    

    Or without last if png

    Stream mapping:
      Stream #0:0 -> #0:0 (hevc (native) -> png (native))
    Press [q] to stop, [?] for help
    

    If disable RAM cache all segments will be lost. Also maybe asking before deleting all video segments would be better? I lost about 40 gpu hours like that.

    enhancement fixed 
    opened by Mimocro 11
  • CUDA not detected for SRMD-CUDA

    CUDA not detected for SRMD-CUDA

    Screenshot (1) It says not compatible with srmd-cuda, with the advice to install cuda on the system, but I do have cuda installed on my system, also tried various versions of cuda, but it still is not working for me. Would appreciate any help

    bug fixed 
    opened by EmreL 11
  • [Feature request] Animated PNG (APNG) support

    [Feature request] Animated PNG (APNG) support

    In a comparison made between GIF, APNG and WebP, it was shown that APNG kept lower file size while keeping at least equal quality. Wikipedia

    Some animated stickers are distributed in APNG format instead of GIF (e.g. Line sticker), but this GUI could only recognize and process them as normal PNGs. I've noticed that both ffmpeg and ImageMagick (>=7.0.10-31) support APNG, which means that pre-processing and post-processing APNG in the similar way to GIF may be feasible.

    enhancement fixed 
    opened by Rongronggg9 10
  • [Feature request] Move source files when done

    [Feature request] Move source files when done

    Is your feature request related to a problem? Please describe. I keep originals around in a folder below each gallery, in a folder called "small". I don't want to delete them, because I want to upscale them again when you update the engines.

    When upscaling many files in many different folders, the list of files in the folders becomes large. It is then annoying to move the originals to the small folder.

    I could set the output folder each time, but that is annoying, because I want the opposite. I also don't know if it takes relative paths.

    Describe the solution you'd like An option next to output folder that asks where to move the source files when done.

    enhancement 
    opened by tehpron 0
  • [Known issue] AMD Optional(Beta) Adrenalin driver not compatible with engines

    [Known issue] AMD Optional(Beta) Adrenalin driver not compatible with engines

    📝Edited by developer:

    v22.5.2 is an optional driver, please go back to recommended driver instead (v22.5.1)

    Since the recently released Nvidia driver and last recommended AMD GPU driver(v22.5.1) both don't have this issue, it's safe to assume this is a driver issue, and since I am not working at AMD, there isn't really much I can do about this other than waiting for AMD to fix their driver.


    ⚠⚠Please read the followings before you create a new issue⚠⚠

    • Be civil and polite.
    • Only BUG Report and Suggestions are allowed here, this is NOT customer-service center.
    • You are only allowed to report bugs you encounter when using Latest version.(Beta/Stable)
    • English and Chinese languages only.
    • Please follow the issue template, and provide all related information. Including what you are trying to do when issue happened, your PC's specification, software settings, and the file you were trying to process. Issue will be deleted if there was not enough information provided.

    Software Version Latest BETA or Latest Stable? Latest Stable (Also tested it with v3.86.74 and had the same issues

    Describe the bug GPU is not being detected by the software. Probably due to the latest driver update. I can't be sure however as I haven't touched the software for quite some time

    How to Reproduce the bug Start the compatibility test and GPU is not being detected

    Expected behavior GPU is supposed to be detected along with the algorithms that supports it

    Screenshots Expected Result: image

    The settings you were using when issue occured I didn't change anything, it happened during the first time setup.

    Desktop (please complete the following information):

    • OS: Windows 10
    • GPU Model: 6900XT
    • CPU Model: 5600X
    • Amount of RAM: 16GB
    • Amount of VRAM: 16GB
    • Amount of Storage: 1TB M.2 NVME, 1TB Hard Drive, 500GB M.2 NVME, 256GB SATA SSD
    BUG Report 
    opened by muoname 3
  • [建议] 建议添加DeOldify的图片/视频上色引擎

    [建议] 建议添加DeOldify的图片/视频上色引擎

    建议描述 建议添加DeOldify处理引擎并在图像处理选项中添加“黑白图像上色”(或者“老照片上色/修复”)支持。 工程链接:https://github.com/jantic/DeOldify Gitee 极速下载 有收录这个项目。 您设想的解决方案 添加功能后可以选择以允许为图像上色。这个功能最好适用于所有放大选项。至于最好应该在放大/补帧前还是放大/补帧后进行上色仍烦请测试。 类似的实现 可以选择看工程链接推荐的那些项目。 补充内容 我搜索到在Issue#60有人提及过DeOldify引擎,但由于只提及一处而且在他的Issue的最后一行作为补充建议,您在回复他时似乎没有发现这行建议。

    enhancement 
    opened by iamPorter 0
  • [Feature request] Batch processing multiple settings

    [Feature request] Batch processing multiple settings

    I often find myself processing the same image or images in batches using multiple settings for the same engine (eg. with different denoise settings or different models) to compare the outputs. The ability to do all of those operations at the same time instead of in small batches could make for a nice enhancement. Perhaps this could be done with checkmarks for each image in the queue or by using something similar to the existing Custom Resolution option?

    I currently use a script based around waifu2x-converter-cpp that I kludged together to do this (and do custom file naming based on the processing variables) but it is nowhere near as versatile as this amazing program you have.

    enhancement 
    opened by Arkbird1000 0
  • [Feature request] MP4 to GIF

    [Feature request] MP4 to GIF

    Currently, I convert MP4 files to GIF using ffmpeg with a -filter_complex setting that looks like this:

    [0:v] split [a][b];
    [a] palettegen=stats_mode=diff:max_colors=256:reserve_transparent=1 [p];
    [b][p] paletteuse=dither=bayer:bayer_scale=5:diff_mode=rectangle [out]
    

    But, it occurred to me that using waifu2x to denoise the frames would likely result in a much better looking and smaller GIF. This project has all the components necessary to streamline the process.

    enhancement 
    opened by ImportTaste 0
Releases(v3.91.23-beta)
PoC black/white image sequence to dumpy gif image sequence converter

PoC black/white image sequence to dumpy gif image sequence converter

null 63 Jun 27, 2022
An image and texture viewer for tga, png, apng, exr, dds, gif, hdr, jpg, tif, ico, webp, and bmp files

An image and texture viewer for tga, png, apng, exr, dds, gif, hdr, jpg, tif, ico, webp, and bmp files. Uses Dear ImGui, OpenGL, and Tacent. Useful for game devs as it displays information like the presence of an alpha channel and querying specific pixels for their colour.

Tristan Grimmer 132 Jun 22, 2022
Import GIF/WebP animated image as a new AnimatedTexture asset type.

Animated Texture Plugin for Unreal Engine 5 This plugin allows you to import animated pictures into your Unreal Engine 5 project as a new AnimatedText

房燕良 21 Jun 20, 2022
Video++, a C++14 high performance video and image processing library.

Video++ Video++ is a video and image processing library taking advantage of the C++14 standard to ease the writing of fast video and image processing

Matthieu Garrigues 681 Jun 14, 2022
A slim, fast and header-only GIF loader written in C

gif_load This is an ANSI C compatible animated GIF loader in a single header file of less than 300 lines of code (less than 200 without empty lines an

Andrey Guskov 63 Apr 17, 2022
This program converts APNG animations into animated GIF format

apng2gif This project has been in disrepair for long time. Recently, there is need to change the number of loops in apng file. So I used it to modify

Ted Zyzsdy 1 Jan 20, 2022
A GIF art engine that will allow you to generate multi-layer GIFs from single GIFs as layers.

A GIF art engine that will allow you to generate multi-layer GIFs from single GIFs as layers. All the code in this repository has been written by me in c++, inspired by the generative art engine of HashLips that does not support GIFs as layers. The problem arose from my and my teamleader's need to generate animated images and then GIFs, in the same way as HashLips generated static images.

Andre 59 Jun 27, 2022
The “Quite OK Image” format for fast, lossless image compression

The “Quite OK Image” format for fast, lossless image compression

Dominic Szablewski 5.6k Jun 24, 2022
Qt5 image viewer with optional video support

Qt5 image viewer with optional video support

null 1.3k Jul 1, 2022
C++ image processing and machine learning library with using of SIMD: SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2, AVX-512, VMX(Altivec) and VSX(Power7), NEON for ARM.

Introduction The Simd Library is a free open source image processing and machine learning library, designed for C and C++ programmers. It provides man

Ihar Yermalayeu 1.6k Jun 24, 2022
ppl.cv is a high-performance image processing library of openPPL supporting x86 and cuda platforms.

ppl.cv is a high-performance image processing library of openPPL supporting x86 and cuda platforms.

null 318 Jun 10, 2022
HDRView is a simple research-oriented image viewer with an emphasis on examining and comparing high-dynamic range (HDR) images

HDRView is a simple research-oriented high-dynamic range image viewer with an emphasis on examining and comparing images, and including minimalistic tonemapping capabilities. HDRView currently supports reading EXR, PNG, TGA, BMP, HDR, JPG, GIF, PNM, PFM, and PSD images and writing EXR, HDR, PNG, TGA, PPM, PFM, and BMP images.

Wojciech Jarosz 103 Jun 16, 2022
The CImg Library is a small and open-source C++ toolkit for image processing

http://cimg.eu The CImg Library is a small and open-source C++ toolkit for image processing, designed with these properties in mind: CImg defines clas

David Tschumperlé 1.1k Jun 27, 2022
Like feh, but better, faster, more image formats, simpler, more lightweight, animation support, and better UI

Like feh, but better, faster, more image formats, simpler, more lightweight, animation support, and better UI

martin 8 Apr 9, 2022
This is a C++17 deployment of deep-learning based image inpainting algorithm on Windows10, using Libtorch, Opencv and Qt.

This is a desktop software for image inpainting. It is a C++ deployment of image inpainting algorithm on Windows10, based on C++17 and implemented using vs2019.

null 4 May 13, 2022
A fast image processing library with low memory needs.

libvips : an image processing library Introduction libvips is a demand-driven, horizontally threaded image processing library. Compared to similar lib

libvips 16 Jun 19, 2022
a generic C++ library for image analysis

VIGRA Computer Vision Library Copyright 1998-2013 by Ullrich Koethe This file is part of the VIGRA computer vision library. You may use,

Ullrich Koethe 368 Jun 25, 2022