{"id":15116986,"url":"https://github.com/TNTwise/REAL-Video-Enhancer","last_synced_at":"2025-09-27T22:31:49.640Z","repository":{"id":177455070,"uuid":"599360014","full_name":"TNTwise/REAL-Video-Enhancer","owner":"TNTwise","description":"Interpolate and Upscale easily on Linux/MacOS/Windows.","archived":false,"fork":false,"pushed_at":"2024-10-29T13:13:58.000Z","size":549170,"stargazers_count":226,"open_issues_count":12,"forks_count":15,"subscribers_count":4,"default_branch":"2.0","last_synced_at":"2024-10-29T15:59:02.020Z","etag":null,"topics":["gui","ifrnet","interpolation","linux","macos","real-esrgan","rife","upscaling","waifu2x"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TNTwise.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":null,"patreon":null,"open_collective":null,"ko_fi":"tntwise","tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":null,"custom":null}},"created_at":"2023-02-09T01:06:20.000Z","updated_at":"2024-10-29T13:14:01.000Z","dependencies_parsed_at":"2024-01-12T23:35:10.707Z","dependency_job_id":"be7ed670-9f76-4607-b889-00c4720570b7","html_url":"https://github.com/TNTwise/REAL-Video-Enhancer","commit_stats":null,"previous_names":["tntwise/rife-esrgan-app-linux-qt","tntwise/real-video-enhancer"],"tags_count":26,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNTwise%2FREAL-Video-Enhancer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNTwise%2FREAL-Video-Enhancer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNTwise%2FREAL-Video-Enhancer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TNTwise%2FREAL-Video-Enhancer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TNTwise","download_url":"https://codeload.github.com/TNTwise/REAL-Video-Enhancer/tar.gz/refs/heads/2.0","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234462097,"owners_count":18837258,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["gui","ifrnet","interpolation","linux","macos","real-esrgan","rife","upscaling","waifu2x"],"created_at":"2024-09-26T01:45:27.716Z","updated_at":"2025-09-27T22:31:49.635Z","avatar_url":"https://github.com/TNTwise.png","language":"Python","readme":"# REAL Video Enhancer\n![Visitors](https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fgithub.com%2FTNTwise%2FREAL-Video-enhancer%2F\u0026countColor=%23263759)\n[![pypresence](https://img.shields.io/badge/using-pypresence-00bb88.svg?style=for-the-badge\u0026logo=discord\u0026logoWidth=20)](https://github.com/qwertyquerty/pypresence)\n\n![license](https://img.shields.io/github/license/tntwise/real-video-enhancer)\n![Version](https://img.shields.io/badge/Version-2.2.0-blue)\n![downloads_total](https://img.shields.io/github/downloads/tntwise/REAL-Video-Enhancer/total.svg?label=downloads%40total)\n\u003ca href=\"https://discord.gg/hwGHXga8ck\"\u003e\n      \u003cimg src=\"https://img.shields.io/discord/1041502781808328704?label=Discord\" alt=\"Discord Shield\"/\u003e\u003c/a\u003e\n\n\u003cp align=center\u003e\n  \u003cimg src=\"https://github.com/TNTwise/REAL-Video-Enhancer/raw/2.0/icons/logo-v2.svg\" width = \"25%\"\u003e\n\u003c/p\u003e\n\n# Table of Contents\n  \n* **[Introduction](#introduction)**\n* **[Features](#Features)**\n* **[Hardware Requirements](#hardware-requirements)**\n* **[Models](#models)**\n  * [Interpolate Models](#interpolate-models)\n  * [Upscale Models](#upscale-models)\n* **[Backends](#backends)**\n* **[FAQ](#faq)**\n  * [General App Usage](#general-application-usage) \n  * [TensorRT](#tensorrt-related-questions)\n  * [ROCm](#rocm-related-questions)\n  * [NCNN](#ncnn-related-questions)\n* **[Cloning](#cloning)**\n* **[Building](#building)**\n* **[Colab Notebook](#colab-notebook)**\n* **[Credits](#credits)**\n  * [People](#people) \n  * [Software](#software)\n\n# Introduction\n\n\u003cstrong\u003eREAL Video Enhancer\u003c/strong\u003e  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 \u003ca rel=\"noopener noreferrer\" href=\"https://nmkd.itch.io/flowframes\" target=\"_blank\" \u003eFlowframes\u003c/a\u003e or \u003ca rel=\"noopener noreferrer\" href=\"https://github.com/mafiosnik777/enhancr\" target=\"_blank\"\u003eenhancr\u003c/a\u003e.\n\n\u003cp align=center\u003e\n  \u003cimg src=\"https://github.com/TNTwise/REAL-Video-Enhancer/blob/a68ab3bc145220e7e4fd0f41a2c7cd2329095f55/screenshots/demo.png?raw=true\" width = \"100%\"\u003e\n\u003c/p\u003e\n\u003ch1\u003eFeatures: \u003c/h1\u003e\n\u003cul\u003e\n  \u003cli\u003e Windows support. \u003cstrong\u003e!!! NOTICE !!!\u003c/strong\u003e The bin can be detected as a trojan. This is a false positive caused by pyinstaller.\u003c/li\u003e\n  \u003cli\u003e Ubuntu 20.04+ suppory on Executable and Flatpak. \u003c/li\u003e\n  \u003cli\u003e MacOS 13+ arm/x86 support \u003c/li\u003e\n  \u003cli\u003e Discord RPC support for Discord system package and Discord flatpak. \u003c/li\u003e\n  \u003cli\u003e Scene change detection to preserve sharp transitions. \u003c/li\u003e\n  \u003cli\u003e Preview that shows latest frame that has been rendered. \u003c/li\u003e\n  \u003cli\u003e TensorRT and NCNN for efficient inference across many GPUs. \u003c/li\u003e\n\u003c/ul\u003e\n\n# Hardware/Software Requirements\n|  | Minimum | Recommended | \n |--|--|--|\n| CPU | Dual Core x64 bit | Quad Core x64 bit\n| GPU | Vulkan 1.3 capable device | Nvidia RTX GPU (20 series and up)\n| RAM | 8 GB | 16 GB\n| Storage | 1 GB free (NCNN install only) | 10 GB free (TensorRT install)\n| Operating System | Windows 10/11 64bit / MacOS 13+ | Any modern Linux distro (Ubuntu 20.04+)\n\n# Models:\n### Interpolate Models:\n| Model | Author | Link |\n|--|--|--|\n| RIFE 4.6,4.7,4.15,4.18,4.22,4.22-lite,4.25 | Hzwer | [Practical-RIFE](https://github.com/hzwer/Practical-RIFE) \n| GMFSS | 98mxr | [GMFSS_Fortuna](https://github.com/98mxr/GMFSS_Fortuna) \n| GIMM | GSeanCDAT | [GIMM](https://github.com/GSeanCDAT/GIMM-VFI) \n\n### Upscale Models:\n| Model | Author | Link |\n|--|--|--|\n| 4x-SPANkendata | Crustaceous D | [4x-SPANkendata](https://openmodeldb.info/models/4x-SPANkendata) \n| 4x-ClearRealityV1 | Kim2091 | [4x-ClearRealityV1](https://openmodeldb.info/models/4x-ClearRealityV1) \n| 4x-Nomos8k-SPAN series | Helaman | [4x-Nomos8k-SPAN series](https://openmodeldb.info/models/4x-Nomos8k-span-otf-strong) \n| 2x-OpenProteus | SiroSky | [OpenProteus](https://github.com/Sirosky/Upscale-Hub/releases/tag/OpenProteus) \n| 2x-AnimeJaNai V2 and V3 Sharp | The Database | [AnimeJanai](https://github.com/the-database/mpv-upscale-2x_animejanai)\n\n# Backends\n  | Backend | Hardware | \n  |--|--|\n  | TensorRT | NVIDIA RTX GPUs\n  | PyTorch  | CUDA 12.6 and ROCm 6.2 capable GPUs\n  | NCNN | Vulkan 1.3 capable GPUs\n \n# FAQ\n### General Application Usage\n  | Question | Answer | \n  |--|--|\n  | What does this program attempt to accomplish? | Fast, efficient and easily accessable video interpolation (Ex: 24-\u003e48FPS) and video upscaling (Ex: 1920-\u003e3840)\n  | 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.\n\n### TensorRT related questions\n  |||\n  |--|--|\n  | 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.\n  | 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.\n \n### ROCm related questions\n  |||\n  |--|--|\n  | Why am I getting (Insert Error here)? | ROCM is buggy, please take a look at \u003ca href=\"https://github.com/TNTwise/REAL-Video-Enhancer/wiki/ROCm-Help\"\u003eROCm Help\u003c/a\u003e.\n\n### NCNN related questions\n  |||\n  |--|--|\n  | 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 \u003ca href=\"https://github.com/TNTwise/REAL-Video-Enhancer-Colab\"\u003eColab Notebook\u003c/a\u003e  instead.\n\n\n# Cloning:\n```\n# Nightly\ngit clone https://github.com/TNTwise/REAL-Video-Enhancer\n\n# Stable\ngit clone https://github.com/TNTwise/REAL-Video-Enhancer --branch 2.2.1\n```\n# Building:\n\n\u003cp\u003e3 supported build methods: \u003c/p\u003e\n\u003cp\u003e - pyinstaller (recommended for Win/Mac) \u003cbr/\u003e\n    - cx_freeze (recommended for Linux) \u003cbr/\u003e\n    - nuitka (experimental)\n\u003c/p\u003e\n\u003cp\u003esupported python versions: \u003c/p\u003e\n\u003cp\u003e - 3.10 3.11, 3.12 \u003cbr/\u003e\n\u003c/p\u003e\n\n```\npython3 build.py --build BUILD_OPTION --copy_backend\n```\n\n# Colab Notebook\n \u003ca href=\"https://colab.research.google.com/github/TNTwise/REAL-Video-Enhancer-Colab/blob/main/RVEColab.ipynb\"\u003eColab Notebook\u003c/a\u003e\n\n# Credits:\n### People:\n| Person | For | Link |\n|--|--|--|\n| NevermindNilas | Some backend and reference code and working with me on many projects | https://github.com/NevermindNilas/ \n| Styler00dollar | RIFE ncnn models (4.1-4.5, 4.7-4.12-lite), Sudo Shuffle Span and benchmarking | https://github.com/styler00dollar \n| HolyWu | TensorRT engine generation code, inference optimizations, and RIFE jagged lines fixes | https://github.com/HolyWu/ \n| Rick Astley | Amazing music | https://www.youtube.com/watch?v=dQw4w9WgXcQ \n\n### Software: \n| Software Used | For | Link|\n|--|--|--|\n| FFmpeg | Multimedia framework for handling video, audio, and other media files | https://ffmpeg.org/ \n| PyTorch | Neural Network Inference (CUDA/ROCm/TensorRT) | https://pytorch.org/ \n| NCNN | Neural Network Inference (Vulkan) | https://github.com/tencent/ncnn \n| RIFE | Real-Time Intermediate Flow Estimation for Video Frame Interpolation | https://github.com/hzwer/Practical-RIFE \n| rife-ncnn-vulkan | Video frame interpolation implementation using NCNN and Vulkan | https://github.com/nihui/rife-ncnn-vulkan \n| rife ncnn vulkan python | Python bindings for RIFE NCNN Vulkan implementation | https://github.com/media2x/rife-ncnn-vulkan-python \n| GMFSS | GMFlow based Anime VFI | https://github.com/98mxr/GMFSS_Fortuna\n| GIMM | Motion Modeling Realistic VFI | https://github.com/GSeanCDAT/GIMM-VFI \n| ncnn python | Python bindings for NCNN Vulkan framework | https://pypi.org/project/ncnn \n| Real-ESRGAN | Upscaling | https://github.com/xinntao/Real-ESRGAN \n| SPAN | Upscaling | https://github.com/hongyuanyu/SPAN \n| Spandrel | CUDA upscaling model architecture support | https://github.com/chaiNNer-org/spandrel \n| cx_Freeze | Tool for creating standalone executables from Python scripts (Linux build) | https://github.com/marcelotduarte/cx_Freeze \n| PyInstaller | Tool for creating standalone executables from Python scripts (Windows/Mac builds) | https://github.com/pyinstaller/pyinstaller\n| Feather Icons | Open source icons library | https://github.com/feathericons/feather \n| PySceneDetect | Transition detection library for python | https://github.com/Breakthrough/PySceneDetect/\n| Python Standalone Builds | Backend inference using portable python, helps when porting to different platforms. | https://github.com/indygreg/python-build-standalone |\n\n\n# Star History\n[![Star History Chart](https://api.star-history.com/svg?repos=tntwise/real-video-enhancer\u0026type=Date)](https://star-history.com/#tntwise/real-video-enhancer\u0026Date)\n","funding_links":["https://ko-fi.com/tntwise"],"categories":["Other","Python"],"sub_categories":["Other"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTNTwise%2FREAL-Video-Enhancer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTNTwise%2FREAL-Video-Enhancer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTNTwise%2FREAL-Video-Enhancer/lists"}