# RIFE

More practical frame interpolation approach.

Repository: https://github.com/hzwer/Practical-RIFE
Canonical: https://ross.abutalabs.com/products/rife
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-27T08:13:43+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 100
- inputs: {"age_days": 1904, "days_push": 6, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1004, forks 129 (observed 2026-09-03T02:15:12.813806+00:00)

## What it is
RIFE is a deep learning model for real-time video frame interpolation, estimating intermediate flow between frames to generate smooth slow-motion or high-framerate video. It supports arbitrary-timestep interpolation and runs 30+ FPS for 2X 720p interpolation on a consumer GPU.

## Use cases
- interpolate video frames to increase framerate
- convert videos to slow motion
- smooth out low-fps anime footage
- upsample frames of AI-generated diffusion videos
- generate intermediate frames between two images

## When to choose
- you need real-time frame interpolation on a GPU
- you want arbitrary-timestep interpolation between frames
- you need a well-cited model with practical pretrained releases for anime and general video

## When to avoid
- you have no GPU available
- you need a turnkey GUI application rather than a model and scripts
- your videos have complex occlusions that flow-based methods handle poorly

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, image-processing
- domain: computer-vision, deep-learning, media
- platform: python, windows
- tags: video-frame-interpolation, optical-flow, slomo, vfi, aigc, eccv2022, video, gpu, linux, macos

## Member repositories
- hzwer/Practical-RIFE (main) score 77
- hzwer/ECCV2022-RIFE (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:12.813806+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 2026-08-29T17:55:37.166262+00:00, confidence not recorded.
  - readme: https://github.com/hzwer/Practical-RIFE (fetched 2026-09-03T02:15:12.813806+00:00, sha bbd8c5b63d75)
- Data as of 2026-08-30T08:39:29.467469+00:00.