


The original video's copyright belongs to ASCII Media WorksĬatfru scaled up to 4x its original size using waifu2x (original image) Image Upscaling.The Pet Girl of Sakurasou: YouTube | Bilibili.The original video's copyright belongs to あにら.The original video's copyright belongs to 株式会社スタジオジブリ.Upscale demo: Spirited Away's movie trailer More information about the algorithms that it supports can be found in the documentations. It can use these following state-of-the-art algorithms to increase the resolution and frame rate of your video/GIF/image. Video2X is a video/GIF/image upscaling and frame interpolation software written in Python. The Wiki is open to edits by the community, so you, yes you, can also correct errors or add new contents to the documentations. It includes comprehensive explanations for how to use the GUI, the CLI, the container image, the library, and more. Video2X's documentations are hosted on this repository's Wiki page. For more information on how to use Video2X's Docker image, please refer to the documentations. If you already have Docker/Podman installed, only one command is needed to start upscaling a video. Video2X container images are available on the GitHub Container Registry for easy deployment on Linux and macOS. You must log in to GitHub to download CI build artifacts. However, they are much less stable to the stable releases. They usually contain more experimental features and bug fixes. Nightly releases are automatically created by the GitHub Actions CI/CD pipelines. Usage instructions are embedded in the Colab Notebook. You can get Colab Pro/Pro+ if you'd like to use better GPUs and get longer runtimes. Please use the free resource fairly and do not create sessions back-to-back and run upscaling 24/7. 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. You can use Video2X on Google Colab for free if you don't have a powerful GPU of your own. Try the mirror if you can't download releases directly from GitHub. Go to the GUI page to see the basic usages of the GUI. GUI is not available for 5.0.0 yet, but is already under development. The latest Windows update is built based on version 4.8.1. Join our Telegram discussion group to ask any questions you have about Video2X, chat directly with the developers, or discuss about upscaling technologies and the future of Video2X in general.
