#25 · Primary category: Video & Animation

video2x

anime4k frame-interpolation machine-learning neural-networks realcugan realesrgan rife super-resoluion upscale-video vulkan

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

Project last updated:03/07/26

GitHub Stars

21.4K

Forks

1.9K

Contributors

26

License

AGPL-3.0

Why we included this project

Video2X bundles several neural upscaling and frame interpolation models, Anime4K, Real-ESRGAN, Real-CUGAN, and RIFE, into a single pipeline. You point it at a video and it returns a higher-resolution, smoother version, so you don't have to run each model separately. The current C/C++ rewrite runs on Windows and Linux with a GUI and installer, and it can use Vulkan-capable GPUs for acceleration, which makes it approachable for people who aren't developers. It's especially popular for cleaning up older anime and archival footage, but the same workflow works on any video you want to sharpen or convert to a higher frame rate. If you need to upscale a lot of footage rather than experiment with research models, this is a solid place to start.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category