Open Source Linux Video Upscalers
Sort By:
Video Upscalers for Linux
View 4 business solutionsBrowse free open source Video Upscalers and projects for Linux below. Use the toggles on the left to filter open source Video Upscalers by OS, license, language, programming language, and project status.
-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
1
Video2X
A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K
A lossless video/GIF/image upscale achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018. The latest Windows update is built based on version 4.8.1. GUI is not available for 5.0.0 yet, but is already under development. Go to the GUI page to see the basic usage of the GUI. Try the mirror if you can't download releases directly from GitHub. You can use Video2X on Google Colab for free if you don't have a powerful GPU of your own. You can borrow a powerful GPU (Tesla K80, T4, P4, or P100) on Google's server for free for a maximum of 12 hours per session. Please use the free resource fairly and do not create sessions back-to-back and run upscaling 24/7. This might result in you getting banned. You can get Colab Pro/Pro+ if you'd like to use better GPUs and get longer runtimes. Usage instructions are embedded in the Colab Notebook. -
2
OptiScaler
OptiScaler bridges upscaling/frame gen across GPUs
OptiScaler is an open-source modding tool designed to enhance graphics performance and flexibility in modern PC games by allowing users to replace or modify built-in upscaling technologies. Instead of relying on the upscaling method originally integrated by a game developer, the software intercepts the game’s rendering pipeline and redirects it to alternative technologies chosen by the user. This makes it possible to swap technologies such as NVIDIA DLSS, AMD FSR, or Intel XeSS even if the game only supports one of them by default. The tool effectively acts as a compatibility layer between the game engine and multiple upscaling frameworks, enabling cross-GPU access to features that might otherwise be restricted to specific hardware ecosystems. In addition to replacing upscalers, OptiScaler can enable frame generation features in titles that do not officially support them, improving frame rates and perceived smoothness during gameplay. -
3
cnc-ddraw
GDI, OpenGL and Direct3D 9 re-implementation of the DirectDraw API
GDI, OpenGL and Direct3D 9 re-implementation of the DirectDraw API for classic games for better compatibility with Windows 2000, XP, Vista, 7, 8, 10, 11, Wine (Linux/macOS) and Virtual Machines. cnc-ddraw can fix compatibility issues in older games, such as black screen, bad performance, crashes or defective Alt+Tab. Supports Windows 2000, XP, Vista, 7, 8, 10, 11, Wine (Linux/macOS) and Virtual Machines. GDI / OpenGL / Direct3D 9 renderer (With automatic renderer selection) Upscaling via glsl shaders. Windowed Mode / Fullscreen Exclusive Mode / Borderless Mode. Alt+Enter support to switch quickly between Fullscreen and Windowed mode. Automatically saves and restores window position/size/state. FPS Limiter, VSync, optional mouse sensitivity scaling. If you use cnc-ddraw with a game that got its own windowed mode built in then make sure you disable the games own windowed mode first. -
4
QualityScaler
Image/video AI upscaler app (BSRGAN)
Qualityscaler is a Windows app that uses BSRGAN Artificial Intelligence to enhance, enlarge and reduce noise in photographs and videos. QualityScaler is completely written in Python, from the backend to the front end. Image/list of images upscale. Video upscale. Drag&drop files [image / multiple images/video] Automatic image tiling and merging to avoid gpu VRAM limitation. Resize image/video before upscaling. Multiple Gpu support. Compatible images - png, jpeg, bmp, webp, tif. Compatible video - mp4, wemb, gif, mkv, flv, avi, mov, qt. -
8 Monitoring Tools in One APM. Install in 5 Minutes.AppSignal works out of the box for Ruby, Elixir, Node.js, Python, and more. 30-day free trial, no credit card required.
-
5
Real-ESRGAN GUI
Cross-platform GUI for image upscaler Real-ESRGAN
The graphic interface of Real-ESRGAN, a practical and beautiful image magnification tool, refers to the design of waifu2x-caffe. This program is a graphical interface of Real-ESRGAN's command line program Real-ESRGAN-ncnn-vulkan , written in Python and tkinter, and supports Windows, Ubuntu and macOS platforms. According to actual measurements, arm64the single-architecture performance is better than universal2the dual- architecture Mac on the Apple chip, so Apple chip users are advised to pack arm64single-architecture applications by themselves. Real-ESRGAN can only enlarge the input image with a fixed 2-4x magnification (related to the selected model). This functionality is achieved by downsampling using a conventional scaling algorithm after multiple calls to Real-ESRGAN. Split each frame of the GIF and record the duration, zoom in one by one and then merge. Drag an image file or directory to any position in the window, and its path can be automatically set as the input. -
6
RENDER96-HD-TEXTURE-PACK
Texture pack for Super Mario 64
A collaboration texture pack for Super Mario 64 with the people over at the OldSchool HD, now known as Render 96, that is made of a compillation of the best results ESRGAN upscaling could make as the base for this project, as well of some of the original textures Nintendo used, and a heavier focus in original textures made by project contributors which will eventually be an overwhelming majority of what this project is made of. The end goal for this project is to use the original sources for every texture in the game when possible, and use that to hopefully achieve 100% accuracy by recreating the textures with the same process and resources Nintendo had at their disposal back in 1996, as well of incorporating elements from the promotional art into the game with ESRGAN upscales as placeholders for the original textures. The team and I will make to fill in the blanks where no texture sources could be found. -
7
SeedVR2 Upscaler ComfyUI
Official SeedVR2 Video Upscaler for ComfyUI
ComfyUI-SeedVR2 Video Upscaler is an open-source integration node for the ComfyUI workflow environment that brings the advanced SeedVR2 video upscaling and restoration model directly into visual AI pipelines. This project packages the SeedVR2 architecture as a custom node for ComfyUI, letting users upscale low-resolution video or imagery inside a node-based interface without needing to write code manually. The underlying SeedVR2 model is known for delivering high-quality video enhancement with strong temporal consistency and improved detail preservation by using diffusion-based techniques that are trained specifically on video sequences. Within the ComfyUI ecosystem, the upscaler integrates with existing nodes and pipelines, making it easier to combine with other processing steps such as denoising, color correction, or format conversion. Enthusiasts often use it for workflows ranging from hobby video enhancement to professional content improvement. -
8
enhancr
Video Frame Interpolation & Super Resolution using NVIDIA's TensorRT
enhancr is an elegant and easy to use GUI for Video Frame Interpolation and Video Upscaling which takes advantage of artificial intelligence - built using node.js and Electron. It was created to enhance the user experience for anyone interested in enhancing video footage using artificial intelligence. The GUI was designed to provide a stunning experience powered by state-of-the-art technologies without feeling clunky and outdated like other alternatives. It features blazing-fast TensorRT inference by NVIDIA, which can speed up AI processes significantly. Pre-packaged, without the need to install Docker or WSL (Windows Subsystem for Linux) - and NCNN inference by Tencent which is lightweight and runs on NVIDIA, AMD and even Apple Silicon - in contrast to the mammoth of an inference PyTorch is, which only runs on NVIDIA GPUs. -
9
Anime4KCPP
A high performance anime upscaler
Anime4KCPP provides an optimized bloc97's Anime4K algorithm version 0.9, and it also provides its own CNN algorithm ACNet, it provides a variety of way to use, including preprocessing and real-time playback, it aims to be a high-performance tool to process both image and video. This project is for learning and the exploration task of the algorithm course in SWJTU. Anime4K is a simple high-quality anime upscale algorithm. Version 0.9 does not use any machine learning approaches and can be very fast in real-time processing or pretreatment. ACNet is a CNN-based anime upscale algorithm. It aims to provide both high-quality and high-performance. HDN mode can better denoise, HDN level is from 1 to 3, higher for better denoising but may cause blur and lack of detail. Cross-platform, building have already tested in Windows, Linux, and macOS. -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
10
Anime Player
Video player for improving quality of hand-drawn images
A video player that enhances the quality of a hand-drawn image using Anime4K's high-performance scaling algorithm. This program is a video player written in the Python programming language using the PySimpleGUI graphical user interface library, an mpv media player, and the Anime4K scaling algorithm . Anime Player is designed to play video and audio files and includes functions such as opening files, URLs and folders, setting image scaling parameters using the Anime4K algorithm, creating an mpv config for watching videos using the Anime4K algorithm on Android, viewing help and information about tuning the algorithm. The player also has support for frame interpolation using SVP. You need to install SVP and VapourSynth to work. -
11
DLSS2FSR
CyberFSR/PotatoFSR (FSR 2.1.2) for Games
Replacing DLSS 2.x with FSR 2.1.2 for various games such as Cyberpunk 2077, Red Dead Redemption 2, etc. It includes a DLL wrapper/injector (winmm.dll) to disable Nvidia GeForce RTX GPU checking, so AMD Radeon / Nvidia GTX users can enjoy the mod. Download the latest relase from Release Page. Extract the contents of the archive next to the game EXE file in your games folder. Make sure the game is running in DX12 mode. Download the latest relase from Release Page. Extract the contents of the archive next to the game EXE file in your games folder. -
12
AI Upscaler for Blender
AI Upscaler for Blender using Real-ESRGAN
Blender add-on to dramatically reduce render times using the Real-ESRGAN upscaler. Rendering an HD image in Blender takes 37 minutes. Upscaling can render a similar quality image in 5 mins total. Any PC or laptop can now do 3D rendering. 4k images can be rendered in the time it would take to render HD 1080p images. HD 1080p images can be rendered in record time on low-end hardware. Installation is easy. Just install the addon. No special hardware or GPU is required. Upscaling is done entirely on the CPU. Blender renders a low-resolution image. The Real-ESRGAN Upscaler upscales the low-resolution image to a higher-resolution image. Real-ESRGAN is a deep learning upscaler that uses neural networks to achieve excellent results by adding in detail when it upscales. -
13
TD-Anime4K
Implementation of Anime4K in TouchDesigner
Anime4K is an upscaler specifically for anime style. This repository is an implementation of Anime4K in TouchDesigner that can be used to upscale low-resolution textures to higher textures. Reduced texture loss, aliasing and banding. -
14
AviSynth AiUpscale v1.2.0
AviSynth+ implementation of Super-Resolution Convolutional Neural
An AviSynth+ implementation of some Super-Resolution Convolutional Neural Networks. Independent luma/chroma upscaling and chroma resampling. Two modes for Video/Photography and Line Art. KrigBilateral option for chroma upscaling/resampling. mpv user shaders of all models for real-time upscaling. Copy AiUpscale.avsi and the Shaders folder to the AviSynth+ plugins folder. The low resolution images were generated using the bicubic filter with Catmull-Rom settings, which is the method commonly used for training super-resolution networks, including those tested here. Note however that as an exception to this, the Anime4K models were trained using the average area downsampling method. The AiUpscale models used for all datasets were the "Photo" models, except for the Manga109 dataset for which the "LineArt" models were used. In the same way, the Waifu2x cunet model was used for the Manga109 dataset, and the upconv_7 model for the rest. -
15
UpscalerJS
Image Upscaling in Javascript. Increase image resolution up to 4x
Image Upscaling in Javascript. Increase image resolution up to 4x using Tensorflow.js. Open source, browser/Node compatibility, and completely free to use under the MIT license. Scale images up to 4x their original size, all in Javascript. UpscalerJS ships with pre-trained models in the box covering a wide variety of use cases. Or bring your own! Browser, Node (CPU and GPU-accelerated), and Service Worker environments all supported. Supports inputs in a wide variety of formats - URL, HTMLImageElement, and more, and by default exports a base64 upscaled string. Pick your Javascript flavor! UpscalerJS ships with ESM and UMD (browser) and ESM and CJS (Node). Close to 100% test coverage, Typescript support, examples covering a wide variety of use cases, and thick documentation. -
16
VSGAN
VapourSynth Single Image Super-Resolution Generative Adversarial
Single Image Super-Resolution Generative Adversarial Network (GAN) which uses the VapourSynth processing framework to handle input and output image data. Transform, Filter, or Enhance your input video, or the VSGAN result with VapourSynth, a Script-based NLE. You can chain models or re-run the model twice-over (or more). Have low VRAM? Don’t worry! The Network will be applied in quadrants of the image to reduce up-front VRAM usage. You can use any RGB video input, including float32 (e.g., RGBS) inputs. Using VapourSynth you can pass a Video directly to VSGAN, without any frame extraction needed. Any edit you make in the VapourSynth script with or without VSGAN can be re-used for any other video. VSGAN is released under the MIT License, ensuring it will stay free, with the ability to be used commercially. -
17
ACNetGLSL
Anime4KCPP Net re-implemented in GLSL for real-time anime upscaling
ACNet is a CNN algorithm, implemented by Anime4KCPP, it aims to provide both high-quality and high performance. This GLSL implementation can be used in MPV player, it is cross-platform. Windows users can also use Anime4KCPP DirectShow Filter for MPC-HC/BE or potplayer. Download the glsl file and MPV player. Copy glsl to the root directory of MPV. Create a file named mpv.conf in the root directory of MPV, and add the following statement (Assume the glsl file name is ACNet.glsl). When playing the video, press Shift + i and then 2 to check if it is enabled. -
18
AI Models
A repository of trained models
All models (at least currently) are supported by chaiNNer, an upscaling GUI that allows for both very simple and very complex tasks to be completed in a nice manner where you "chain" nodes together. Highly recommended for images. If you're looking to upscale videos using the models then use enhancr simply due to the fact that it supports TensorRT, which will allow you to upscale videos at incredible speeds! The GUI is one of the best looking applications out there and is personally my go to option. While yes builds are paid, it is well worth your money and beats any other GUI out there currently. -
19
Anime4K-rs
An attempt to write Anime4K in Rust
An attempt to write Anime4K in Rust. Anime4K is a state-of-the-art*, open-source, high-quality real-time anime upscaling algorithm that can be implemented in any programming language. -
20
Anime4kSharp
Anime4K implemented in C#
Anime4KSharp is a .Net Core library that implements bloc97's Anime4K Algorithm version 0.9 and 1.0 RC2. The Algorithm is executed on the CPU, but utilizing all available CPU Cores. This yields to a conversion time of "only" 4432 ms when upscaling from 1080p to 2160p. This time could possibly be reduced with further optimization. Images are processed in four phases that are executed on a pixel- per- pixel basis. Each phase takes a input image and renders it to a output image. This makes it easy to port the algorithm (back) to GLSL fragment shaders. As bloc97 described in his pseudo-preprint, the Anime4K algorithm is actually quite simple. -
21
Easy Upscale
A simple image upscaler application using EDSR, ESPCN, FSRCNN, etc.
This application was made to fulfill the assignment for the Data Structures course. The concept of the application is an application to upgrade/enhance image quality. The main theme is queues, we implement circular queues for pooling/storing a list of images to be upscaled. Gui creation is made manually using the tkinter library. For the upscale process itself, it uses the OpenCV library with a model obtained from open source. Checked using vermin. Minimum required versions: 3.6 Incompatible versions: 2. -
22
G2SConverter
Convert models from GoldSource engine to Source engine with AI
Convert models from GoldSource engine to the Source engine with AI. This utility converts GoldSource engine models to Source engine models. A feature of this utility is the ability to improve the quality of textures of models using Upscaling, deblurring, and normal map generating. All operations to improve the quality of textures are performed by neural networks. To improve the quality of the texture, it is first Upscaled using RealESRGAN. The user can select scaling factor: x2, x4 or x8. After the Upscaling procedure, the texture is deblured using the Scale-recurrent Network for Deep Image Deblurring. An example of a processed texture is shown in the following image (parameters used: scaling-factor = 4 and deblur iterations = 4) besides upscaling and debluring the utility also generates normal maps for each texture. This is implemented using the DeepBump by HugoTiny model. Examples of normal maps are shown in the following images. -
23
MNIST-WGAN
A C# WGAN
This project generates hand-written digits from the MNIST dataset using WGAN architecture. While debugged, a few lingering issues may remain, if you encounter any please submit them and they will be resolved. The sources and features of the project can be found in the wiki. Before use, one should verify that the network architecture is as-desired. This may be done with the GUI to the right of the number display. The "Default" button resets the network to hard-coded values which I have verified function. The "Reset" button sets the ACTIVE network to whatever architecture is displayed. In order to change which network is displayed, use the "Critic [1] or Generator [0]" checkbox. To begin training the network, press the "Train" button, after which you may use the "Clear" button to reset the average error and average percent correct value textboxes. In order to use the project on an alternative dataset, one must replace the MNIST files, then rewrite IO.FindNextNumber. -
24
Super-résolution via CNN
Super resolution using a CNN, based on the work of the DGtal team
Super-resolution using a CNN, based on the work of the DGtal team. First of all, an Nvidia graphics card (neither AMD nor Intel integrated) is highly recommended to parallelize the CNN. You will then need to install CUDA. No CUDA = dozens of times slower. This program will generate "model_epoch_ .pth" files corresponding to the model at epoch n, in a folder saved_model_u t_bs bs_tbs tbs_lr lr, where corresponds to the scale factor, bsthe size of the training batch, tbsthe size of the test batch and lrto the learning rate. Low res images should be located in a "dataset/input" folder, and high res targets in a "dataset/target" folder, where each different quality image has the same name in both folders. -
25
Upscale
This program is upscaling any image by a factor 2 using an algorithm
This program is upscaling any image by a factor 2 using an algorithm of cubic interpolation. You may need to install the following libraries to run the program, tqdm, itertools, and OpenCV.
