REAL Video Enhancer

February 11, 2026 ยท View on GitHub

Visitors pypresence

license Version downloads_total Discord Shield

Download on Steam!
Download on Steam

Table of Contents

Introduction

REAL Video Enhancer is a redesigned and enhanced version of the original Rife ESRGAN App for Linux. This program offers convenient access to frame interpolation and upscaling functionalities on Windows, Linux and MacOS, and is an alternative to outdated software like Flowframes or enhancr.

Features:

  • Windows support. !!! NOTICE !!! The bin can be detected as a trojan. This is a false positive caused by pyinstaller.
  • Ubuntu 22.04+ support on Executable and Flatpak. (20.04 can work but is now legacy)
  • MacOS 15+ arm/x86 support
  • Discord RPC support for Discord system package and Discord flatpak.
  • Scene change detection to preserve sharp transitions.
  • Preview that shows latest frame that has been rendered.
  • TensorRT and NCNN for efficient inference across many GPUs.

Hardware/Software Requirements

MinimumRecommended
CPUDual Core x64 bitQuad Core x64 bit
GPUVulkan 1.3 capable deviceNvidia RTX GPU (20 series and up)
VRAM4 GB - NCNN8 GB - TensorRT (Nvidia, why keep making 8gb cards?)
RAM16 GB32 GB
Storage1 GB free - NCNN16 GB free - TensorRT
Operating SystemWindows 10/11 64bit / MacOS 14+Any modern Linux distro (Ubuntu 22.04+)

Models:

Interpolate Models:

ModelAuthorLink
RIFE 4.6,4.7,4.15,4.18,4.22,4.22-lite,4.25HzwerPractical-RIFE
GMFSS98mxrGMFSS_Fortuna
IFRNetltkong218IFRnet

Upscale Models:

ModelAuthorLink
4x-SPANkendataCrustaceous D4x-SPANkendata
4x-Nomos8k-SPAN seriesHelaman4x-Nomos8k-SPAN series
2x-OpenProteusSiroSkyOpenProteus
2x-AnimeJaNai V2 and V3 SharpThe DatabaseAnimeJanai
2x-AniSDSiroSkyAniSD
AnimeSRTencent ARCAnimeSR

Decompression Models:

ModelAuthorLink
DeH264Helaman1xDeH264_realplksr

Denoise Models:

ModelAuthorLink
DRUnetcsznDRUnet
DnCNNczsnDnCNN

Backends

BackendHardware
TensorRTNVIDIA RTX GPUs
PyTorchCUDA 12.6 and ROCm 6.2 capable GPUs
NCNNVulkan 1.3 capable GPUs

FAQ

General Application Usage

QuestionAnswer
What does this program attempt to accomplish?Fast, efficient and easily accessable video interpolation (Ex: 24->48FPS) and video upscaling (Ex: 1920->3840)
Why is it failing to recognize installed backends?REAL Video Enhancer uses PIP and portable python for inference, this can sometimes have issues installing. Please attempt reinstalling the app before creating an issue.
Why does it take so long to begin inference?TensorRT uses advanced optimization at the beginning of inference based on your device, this is only done once per resolution of video inputed.
Why does the optimization and inference fail?The most common way an optimization can fail is Limited VRAM There is no fix to this except using CUDA or NCNN instead.
Why am I getting (Insert Error here)?ROCM is buggy, please take a look at ROCm Help.
Why am I getting (Insert Vulkan Error here)?This usually is an OOM (Out Of Memory) error, this can indicate a weak iGPU or very old GPU, I recommeding trying out the Colab Notebook instead.

Cloning:

# Nightly
git clone --recurse-submodules https://github.com/TNTwise/REAL-Video-Enhancer 

# Stable
git clone --recurse-submodules https://github.com/TNTwise/REAL-Video-Enhancer --branch 2.4.1

Building:

3 supported build methods:

- pyinstaller (recommended for Win/Mac)
- cx_freeze (recommended for Linux)
- nuitka (experimental)

supported python versions:

- 3.10 3.11, 3.12 

python3 build.py --build BUILD_OPTION --copy_backend

Colab Notebook

Colab Notebook

Credits:

People:

PersonForLink
NevermindNilasSome backend and reference code and working with me on many projectshttps://github.com/NevermindNilas/
Styler00dollarRIFE ncnn models (4.1-4.5, 4.7-4.12-lite), Sudo Shuffle Span, and Scene Detect Modelshttps://github.com/styler00dollar
HolyWuTensorRT engine generation code, inference optimizations, and RIFE jagged lines fixeshttps://github.com/HolyWu/
Rick AstleyAmazing musichttps://www.youtube.com/watch?v=dQw4w9WgXcQ

Software:

Software UsedForLink
FFmpegMultimedia framework for handling video, audio, and other media fileshttps://ffmpeg.org/
QTGUI frameworkhttps://qt.io/
FFMpeg BuildsPre-compiled builds of FFMpeg.Windows/Linux: https://github.com/BtbN/FFmpeg-Builds, MacOS: https://github.com/eko5624/mpv-mac
PyTorchNeural Network Inference (CUDA/ROCm/TensorRT)https://pytorch.org/
NCNNNeural Network Inference (Vulkan)https://github.com/tencent/ncnn
RIFEReal-Time Intermediate Flow Estimation for Video Frame Interpolationhttps://github.com/hzwer/Practical-RIFE
rife-ncnn-vulkanVideo frame interpolation implementation using NCNN and Vulkanhttps://github.com/nihui/rife-ncnn-vulkan
rife ncnn vulkan pythonPython bindings for RIFE NCNN Vulkan implementationhttps://github.com/media2x/rife-ncnn-vulkan-python
GMFSSGMFlow based Anime VFIhttps://github.com/98mxr/GMFSS_Fortuna
GIMMMotion Modeling Realistic VFIhttps://github.com/GSeanCDAT/GIMM-VFI
ncnn pythonPython bindings for NCNN Vulkan frameworkhttps://pypi.org/project/ncnn
Real-ESRGANUpscalinghttps://github.com/xinntao/Real-ESRGAN
SPANUpscalinghttps://github.com/hongyuanyu/SPAN
SpandrelCUDA upscaling model architecture supporthttps://github.com/chaiNNer-org/spandrel
ChaiNNerModel Scale Detectionhttps://github.com/chaiNNer-org/chainner
cx_FreezeTool for creating standalone executables from Python scripts (Linux build)https://github.com/marcelotduarte/cx_Freeze
PyInstallerTool for creating standalone executables from Python scripts (Windows/Mac builds)https://github.com/pyinstaller/pyinstaller
Feather IconsOpen source icons libraryhttps://github.com/feathericons/feather
PySceneDetectTransition detection library for pythonhttps://github.com/Breakthrough/PySceneDetect/
Python Standalone BuildsBackend inference using portable python, helps when porting to different platforms.https://github.com/indygreg/python-build-standalone

Star History

Star History Chart