Practical-RIFE
An open-source AI frame interpolation tool that processes video locally, builds on RIFE and SAFA, and supports Apple Silicon acceleration under an MIT license.
Practical-RIFE is a local AI frame interpolation tool for engineers and developers working with video. It generates intermediate frames to increase frame rates, with models intended for ordinary footage, animation, and post-processing videos made by diffusion models. The Python project builds on RIFE and SAFA, with an emphasis on how the output looks rather than improvements in numerical image-quality scores alone.
It accepts video files or PNG frame sequences and can produce double or quadruple the input frame rate. You can also choose the output frame rate directly. For higher-resolution footage, including 4K, it supports processing at a reduced scale. A side-by-side comparison output lets you inspect the interpolated video alongside the original.
The model selection includes lighter variants that require less computation. Animation is a particular focus of model development and testing, so it's relevant to developers building anime interpolation workflows as well as those processing filmed footage. Apple Silicon acceleration is supported through MPS.
This is a code-oriented project for people incorporating interpolation into their own processing workflows. The maintainers direct general users toward SVFI, RIFE-App, and FlowFrames for packaged applications. Practical-RIFE is open source under the MIT license, and its downloadable trained models use the same license.
