awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
Justin62628 avatar

Justin62628/Squirrel-RIFE

0
View on GitHub↗
3,471 stars·181 forks·Python·gpl-3.0·17 views

Squirrel RIFE

Squirrel-RIFE is a GPU-accelerated video processing tool that uses a neural network to generate intermediate frames between existing video frames, enabling smooth slow-motion effects and frame rate conversion. It is built around the RIFE (Real-Time Intermediate Flow Estimation) model, which analyzes motion between consecutive frames to predict and insert new frames, and leverages NVIDIA CUDA for parallel processing to achieve high-speed inference.

The tool distinguishes itself by combining neural frame interpolation with practical video preprocessing features, including pixel-level duplicate frame detection and removal to eliminate stuttering in animated content, and a scene transition detector that identifies cuts with high accuracy to avoid generating interpolated frames across scene changes. It integrates FFmpeg as its video I/O layer for decoding source files and encoding output, and includes an arbitrary frame rate calculator that computes the exact number of intermediate frames needed for conversion between any input and output frame rates without rounding errors.

Squirrel-RIFE processes video frames in parallel batches to maximize GPU utilization, and its capabilities extend to generating smooth slow-motion video from standard-speed footage. The tool is available as a Python application with documentation covering installation and usage.

Features

  • RIFE Model Engines - Executes the RIFE neural network model to generate intermediate frames by analyzing motion between consecutive frames.
  • Video Frame Interpolation Tools - Generates intermediate frames between existing video frames using a neural network to increase frame rate or create smooth slow-motion effects.
  • Frame Interpolation Networks - Uses a neural network on NVIDIA GPUs to predict and insert intermediate frames between existing video frames in parallel.
  • GPU-Accelerated Inference - Leverages NVIDIA GPU parallel processing to run the RIFE model at high speed for real-time frame generation.
  • Batch Video Processing - Processes multiple video frames in parallel batches to maximize GPU utilization and throughput.
  • Batch Frame Processing Pipelines - Processes multiple video frames simultaneously in batches to maximize GPU throughput and reduce per-frame overhead.
  • Batch Frame Processors - Processes multiple video frames in parallel batches to maximize GPU utilization and throughput.
  • CUDA Batch Processing Pipelines - Processes multiple video frames in parallel batches on NVIDIA GPUs to maximize throughput and reduce per-frame overhead.
  • Slow Motion Video Generation - Generates extra frames from standard-speed footage to produce smooth slow-motion effects without stuttering.
  • CUDA-Accelerated Frame Processors - Leverages NVIDIA CUDA for parallel GPU processing to run frame interpolation models at high speed.
  • Frame Rate Converters - Converts between arbitrary input and output frame rates by calculating the exact number of intermediate frames needed.
  • Frame Interpolation Engines - Creates intermediate frames between existing ones using a frame interpolation algorithm to increase frame rate for smoother playback.
  • Video Frame Duplicate Detectors - Compares consecutive frames pixel-by-pixel to identify and remove exact duplicates before interpolation.
  • Animation Stutter Removers - Detects and removes duplicate frames in animated content to eliminate the clipped or jerky appearance.
  • Video Frame Duplicate Detectors - Compares consecutive frames pixel-by-pixel to identify and remove exact duplicates before interpolation.
  • Video Transition Detection - Detects scene transitions with over 95% accuracy to prevent interpolation artifacts across cuts.
  • Video Frame Duplicate Removers - Compares consecutive frames pixel-by-pixel to identify and eliminate exact duplicates before interpolation.
  • Arbitrary Frame Rate Calculators - Calculates exact intermediate frame counts for converting between arbitrary input and output frame rates.
  • Arbitrary Frame Rate Converters - Calculates the exact number of intermediate frames needed to convert between any input and output frame rates.
  • Video Scene Transition Detectors - Identifies scene changes in video with high accuracy to avoid generating interpolated frames across cuts that would cause artifacts.

Star history

Star history chart for justin62628/squirrel-rifeStar history chart for justin62628/squirrel-rife

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does justin62628/squirrel-rife do?

Squirrel-RIFE is a GPU-accelerated video processing tool that uses a neural network to generate intermediate frames between existing video frames, enabling smooth slow-motion effects and frame rate conversion. It is built around the RIFE (Real-Time Intermediate Flow Estimation) model, which analyzes motion between consecutive frames to predict and insert new frames, and leverages NVIDIA CUDA for parallel processing to achieve high-speed inference.

What are the main features of justin62628/squirrel-rife?

The main features of justin62628/squirrel-rife are: RIFE Model Engines, Video Frame Interpolation Tools, Frame Interpolation Networks, GPU-Accelerated Inference, Batch Video Processing, Batch Frame Processing Pipelines, Batch Frame Processors, CUDA Batch Processing Pipelines.

Which projects share features with justin62628/squirrel-rife?

Projects with overlapping indexed features include: baowenbo/dain — DAIN is a video frame synthesis engine and AI video upsampling tool designed to increase video playback smoothness. It… tntwise/real-video-enhancer — Real-Video-Enhancer is a cross-platform desktop application that utilizes neural networks to upscale resolution,… aaronfeng753/waifu2x-extension-gui — Waifu2x-Extension-GUI is a desktop application designed for high-fidelity media restoration and enhancement. It… k4yt3x/video2x — Video2x is a modular processing framework designed for AI-enhanced video upscaling and frame rate conversion. It… nvidia/isaac-gr00t. yaofanguk/video-subtitle-extractor — This project is an optical character recognition tool designed to extract hardcoded subtitles from video frames and…

Projects sharing features with Squirrel RIFE

These projects share indexed features with Squirrel RIFE. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • baowenbo/dainbaowenbo avatar

    baowenbo/DAIN

    8,311View on GitHub↗

    DAIN is a video frame synthesis engine and AI video upsampling tool designed to increase video playback smoothness. It functions as a computer vision model that synthesizes intermediate frames between existing images to transform low frame rate video into high frame rate content. The system utilizes depth-aware video frame interpolation to predict the motion of pixels between consecutive images. By analyzing spatial depth via depth maps, the tool generates new frames that account for occlusions and overlapping objects to create slow motion effects. The framework incorporates optical flow int

    Python
    View on GitHub↗8,311
  • tntwise/real-video-enhancerTNTwise avatar

    TNTwise/REAL-Video-Enhancer

    2,137View on GitHub↗

    Real-Video-Enhancer is a cross-platform desktop application that utilizes neural networks to upscale resolution, generate intermediate frames, and denoise video files. It functions as a deep learning video processor that runs restoration models through hardware acceleration, dispatching heavy prediction workloads directly to underlying graphics hardware. The software executes optical-flow-based frame interpolation to increase framerates and motion smoothness, alongside dedicated filtering models that remove digital noise and blocky compression artifacts from compressed video streams. Additio

    Pythonguiinterpolationlinux
    View on GitHub↗2,137
  • aaronfeng753/waifu2x-extension-guiAaronFeng753 avatar

    AaronFeng753/Waifu2x-Extension-GUI

    16,146View on GitHub↗

    Waifu2x-Extension-GUI is a desktop application designed for high-fidelity media restoration and enhancement. It functions as a graphical interface that orchestrates specialized deep learning engines to upscale, denoise, and interpolate images and videos, improving visual clarity and motion smoothness. The software distinguishes itself through its ability to manage complex, automated media processing pipelines. Users can chain multiple tasks—such as format conversion, scene detection, and frame rate interpolation—into sequential workflows that execute without manual intervention. It provides g

    C++animeanime4kesrgan
    View on GitHub↗16,146
  • k4yt3x/video2xk4yt3x avatar

    k4yt3x/video2x

    18,754View on GitHub↗

    Video2x is a modular processing framework designed for AI-enhanced video upscaling and frame rate conversion. It functions as a comprehensive toolset for increasing the resolution and visual clarity of media files while generating intermediate frames to improve motion smoothness. The system is built to handle intensive media transformation tasks by leveraging hardware acceleration and custom encoding pipelines. The project distinguishes itself through a plugin-based architecture that allows for the integration of custom machine learning models and specialized algorithms. It utilizes a modular

    C++anime4kframe-interpolationmachine-learning
    View on GitHub↗18,754
Compare all 30 related projects→