# nihui/rife-ncnn-vulkan

RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library

Repository: https://github.com/nihui/rife-ncnn-vulkan
Canonical: https://ross.abutalabs.com/products/rife-ncnn-vulkan
Language: C
License: MIT
License Family: permissive
Topics: ncnn, gpu, video-interpolation, vulkan, rife
Last push: 2024-01-02T06:05:10+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2110, "days_push": 974, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1083, forks 93 (observed 2026-08-28T04:03:31.153863+00:00)

## What it is
A command-line tool implementing RIFE (Real-Time Intermediate Flow Estimation) for video frame interpolation using the ncnn neural network inference framework with Vulkan GPU acceleration. It ships portable binaries and models for Windows, Linux, and macOS, requiring no CUDA or PyTorch runtime.

## Use cases
- interpolate frames in a video to increase its frame rate
- generate an in-between frame from two input images
- convert 24fps video to smooth 48fps or 60fps
- slow-motion video creation via frame interpolation
- run AI frame interpolation on GPU without CUDA or PyTorch
- batch interpolate a directory of extracted video frames

## When to choose
- you need portable, dependency-free frame interpolation binaries across Windows/Linux/macOS
- you want GPU-accelerated interpolation on Intel/AMD/Nvidia hardware via Vulkan
- you plan to combine with FFmpeg for full video upscaling of frame rate

## When to avoid
- you need a Python library API rather than a CLI tool
- you require CUDA-optimized performance with PyTorch-based RIFE implementations
- you work only with CPU-only machines without Vulkan support

## Facets
- artifact type: cli-tool
- maturity: active
- function: video-processing, machine-learning, image-processing
- domain: machine-learning, media
- platform: windows, cli
- tags: rife, frame-interpolation, ncnn, vulkan, video-frame-interpolation, video, linux, macos, gpu

## Member repositories
- nihui/rife-ncnn-vulkan (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.153863+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:51:11.728679+00:00, confidence not recorded.
  - readme: https://github.com/nihui/rife-ncnn-vulkan (fetched 2026-08-28T04:03:31.153863+00:00, sha 82a9a3104e8c)
- Data as of 2026-08-30T08:39:29.467469+00:00.