#264 · Primary category: Video & Animation

enhancr

amd artificial-intelligence cain dpir electron esrgan frame-interpolation gmfss intel ncnn nvidia realcugan realesrgan rife super-resolution swinir tensorrt upscaling vapoursynth video-processing

Video Frame Interpolation & Super Resolution using NVIDIA's TensorRT & Tencent's NCNN inference, beautifully crafted and packaged into a single app

Project last updated:01/15/24

GitHub Stars

814

Forks

48

Contributors

6

License

GPL-3.0

Why we included this project

enhancr wraps a set of well-known AI video models in an Electron desktop app, so you can smooth motion and sharpen footage without touching a command line. It covers frame interpolation with RIFE, GMFSS, and CAIN, and upscaling with RealESRGAN, RealCUGAN, and SwinIR, and lets you chain those steps in a single pass. Instead of relying on PyTorch, it runs inference through NVIDIA's TensorRT and Tencent's NCNN, which keeps it light and means it works on AMD and Apple Silicon machines as well as NVIDIA GPUs. The app also has a batch queue, live preview, scene detection to avoid interpolation artifacts on cuts, and video trimming, plus support for loading custom ESRGAN models in ONNX or PyTorch format. If you want a self-contained way to improve video quality on your own hardware, this is a practical 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