The latest Windows update is built based on version 4.8.1. GUI is not available for 5.0.0 yet, but is already under development. Go to the **[Quick Start](#quick-start)** section for usages. Try the [mirror](https://files.k4yt3x.com/Projects/Video2X/lates) if you can't download releases directly from GitHub.
You can use Video2X on [Google Colab](https://colab.research.google.com/) **for free** if you don't have a powerful GPU of your own. You can borrow a powerful GPU (Tesla K80, T4, P4, or P100) on Google's server for free for a maximum of 12 hours per session. **Please use the free resource fairly** and do not create sessions back-to-back and run upscaling 24/7. This might result in you getting banned. You can get [Colab Pro/Pro+](https://colab.research.google.com/signup/pricing) if you'd like to use better GPUs and get longer runtimes. Usage instructions are embedded in the [Colab Notebook](https://github.com/k4yt3x/video2x/actions/workflows/ci.yml).
Nightly releases are automatically created by the GitHub Actions CI/CD pipelines. They usually contain more experimental features and bug fixes. However, they are much less stable to the stable releases. **You must log in to GitHub to download CI build artifacts.**
Video2X container images are available on the GitHub Container Registry for easy deployment on Linux and macOS. If you already have Docker/Podman installed, only one command is needed to start upscaling a video. For more information on how to use Video2X's Docker image, please refer to the [documentations (outdated)](https://github.com/K4YT3X/video2x/wiki/Docker).
Video2X is a video/GIF/image upscaling software based on Waifu2X, Anime4K, SRMD and RealSR written in Python 3. It upscales videos, GIFs and images, restoring details from low-resolution inputs. Video2X also accepts GIF input to video output and video input to GIF output.
Clip is from trailer of animated movie "千と千尋の神隠し". Copyright belongs to "株式会社スタジオジブリ (STUDIO GHIBLI INC.)". Will delete immediately if use of clip is in violation of copyright.
This original input GIF is 160x120 in size. This image is downsized and accelerated to 20 FPS from its [original image](https://gfycat.com/craftyeasygoingankole-capoo-bug-cat).
[Original image](https://72915.tumblr.com/post/173793265673) from [nananicu@twitter](https://twitter.com/nananicu/status/994546266968281088), edited by K4YT3X.
If you can't find a video clip to begin with, or if you want to see a before-after comparison, we have prepared some sample clips for you. The quick start guide down below will also be based on the name of the sample clips.
Clip is from anime "さくら荘のペットな彼女". Copyright belongs to "株式会社アニプレックス (Aniplex Inc.)". Will delete immediately if use of clip is in violation of copyright.
Tweak the settings if you want to, then hit the start button at the bottom and the upscale will start. Now you'll just have to wait for it to complete.
If you would like to tweak engine-specific settings, either specify the corresponding argument after `--`, or edit the corresponding field in the configuration file `video2x.yaml`. **Command line arguments will overwrite default values in the config file.**
This example below adds enables TTA for `waifu2x-caffe`.
To see a help page for driver-specific settings, use `-d` to select the driver and append `-- --help` as demonstrated below. This will print all driver-specific settings and descriptions.
Video2X can be deployed via Docker. The following command upscales the video `sample_input.mp4` with Waifu2X ncnn Vulkan and outputs the upscaled video to `output.mp4`. For more details on Video2X Docker image usages, please refer to the [documentations (outdated)](https://github.com/K4YT3X/video2x/wiki/Docker).
```shell
docker run -it --rm \ # temporary container, delete after run
--gpus all -v /dev/dri:/dev/dri \ # mount GPUs
-v $PWD:/host \ # bind mount the current directory as the container's /host
ghcr.io/k4yt3x/video2x:5.0.0-beta1-cuda \ # the URL of the docker image
-i sample_input.mp4 \ # path of the input file
-o output.mp4 \ # the path to write the output
-p5 \ # launch 5 processes
upscale \ # set action to upscale
-h 720 \ # set output hight to 720 pixels
-d waifu2x \ # use driver waifu2x
-n3 # noise level 3
```
To interpolate a video, set the action to `interpolate`. Right now, only 2x framerate is supported.
You can find all detailed user-facing and developer-facing documentations in the [Video2X Wiki](https://github.com/k4yt3x/video2x/wiki). It covers everything from step-by-step instructions for beginners, to the code structure of this program for advanced users and developers. If this README page doesn't answer all your questions, the wiki page is where you should head to.
Go to the [Drivers](https://github.com/k4yt3x/video2x/wiki/Drivers) wiki page if you want to see a detailed description on the different types of drivers implemented by Video2X. This wiki page contains detailed difference between different drivers, and how to download and set each of them up for Video2X.
If you have any questions, first try visiting our [Q&A](https://github.com/k4yt3x/video2x/wiki/Q&A) page to see if your question is answered there. If not, open an issue and we will respond to your questions ASAP. Alternatively, you can also join our [Telegram discussion group](https://t.me/video2x) and ask your questions there.
Are you interested in how the idea of Video2X was born? Do you want to know the stories and histories behind Video2X's development? Come into this page.
- [Dandere2x](https://github.com/CardinalPanda/dandere2x): A lossy video upscaler also built around `waifu2x`, but with video compression techniques to shorten the time needed to process a video.
- [Waifu2x-Extension-GUI](https://github.com/AaronFeng753/Waifu2x-Extension-GUI): A similar project that focuses more and only on building a better graphical user interface. It is built using C++ and Qt5, and currently only supports the Windows platform.
