Video2X

Free plan LinuxMacSelf-hostedWindows

What Video2X is

Video2X is a free, machine-learning framework for video upscaling and frame interpolation. It supports filtering for super resolution, frame interpolation, or both, using Anime4K v4, Real-ESRGAN, Real-CUGAN, and RIFE models. Custom MPV-compatible GLSL shaders are also supported. Real-ESRGAN, Real-CUGAN, and RIFE run through ncnn and Vulkan. Windows users can install a release with a graphical interface; Linux users can use Arch packages or an AppImage for other distributions. The project also provides container images for Linux and macOS through Docker or Podman. A Google Colab notebook can use free NVIDIA T4, L4, or A100 GPUs for sessions lasting up to 12 hours, an option described for people without a powerful GPU. Precompiled binaries require an AVX2-capable CPU and Vulkan-capable GPU. The project says processing needs no additional disk space beyond the final output. Video2X was founded in 2018 and uses the GNU AGPL version 3 license. Documentation covers building, installation, use, and development, with Telegram support for questions.

Who it suits

It suits users on Windows, Linux, or macOS who need video upscaling, interpolation, or both. Colab is intended for people without a powerful local GPU.

What it does well

Free plan available
Supports upscaling and frame interpolation
Includes several named models
Windows GUI and Linux packages available
Colab GPU sessions offered

What to know first

Precompiled binaries require AVX2 CPU
Precompiled binaries require Vulkan GPU
Colab sessions last up to 12 hours
Some documentation pages are under construction

Limits

Google Colab GPU use is limited to 12 hours per session. Precompiled binaries require an AVX2-capable CPU and a Vulkan-capable GPU.

Getting started

Open the Video2X GitHub repository
Choose a Windows installer, Linux package, or container image
Install with the listed documentation
Select an upscaling or interpolation model
Use Google Colab for a free GPU session if needed

Verdict

Video2X combines multiple enhancement and interpolation models with desktop, container, and Colab options. Hardware requirements and session limits should guide how you deploy it.

Questions

Is Video2X free?

Yes. Video2X has a free plan and no free trial is listed.

Which platforms does it support?

It supports Windows, Linux, and macOS, with container deployment on Linux and macOS.

Which models are available?

Supported models include Anime4K v4, Real-ESRGAN, Real-CUGAN, and RIFE, plus custom MPV-compatible GLSL shaders.

What license does Video2X use?

Video2X is licensed under GNU AGPL version 3.

Who makes Video2X and when was it founded?

The project was founded in 2018.

Can I use a GPU in the cloud?

Yes. Its Google Colab notebook can use free NVIDIA T4, L4, or A100 GPUs for up to 12 hours per session.

Facts from Video2X's own pages

Acceleration: Real-ESRGAN, Real-CUGAN, and RIFE run via ncnn and Vulkan. · github.com, 7 Oct 2026
Cloud use: The project describes using Video2X on Google Colab, with free GPU sessions limited to 12 hours per session. · github.com, 7 Oct 2026
Colab: The project offers a Google Colab notebook that can use free NVIDIA T4, L4, or A100 GPUs for up to 12 hours per session. · github.com, 7 Oct 2026
Containers: Container images are available through GitHub Container Registry for deployment on Linux and macOS using Docker or Podman. · github.com, 7 Oct 2026
Container support: Container images are available through GitHub Container Registry for deployment on Linux and macOS, using Docker or Podman. · github.com, 7 Oct 2026
Custom shaders: It supports custom MPV compatible GLSL shaders. · github.com, 7 Oct 2026
Disk space: The project says processing needs no additional disk space beyond space for the final output. · github.com, 7 Oct 2026
Documentation: The documentation covers building, installing, using, and developing Video2X, and notes that some pages are under construction. · docs.video2x.org, 7 Oct 2026
Founded: 2018 · github.com, 28 Sept 2026
Hardware requirements: Precompiled binaries require an AVX2 capable CPU and a Vulkan capable GPU. · github.com, 7 Oct 2026
Help and documentation: The project links documentation for building, installing, using, and developing Video2X, plus a Telegram discussion group where users can ask developers questions. · github.com, 7 Oct 2026
Intended users: The project describes its Colab option as useful for people who do not have a powerful GPU of their own. · github.com, 7 Oct 2026
Interpolation models: It supports RIFE models through ncnn and Vulkan. · github.com, 7 Oct 2026
License: Video2X is licensed under GNU AGPL version 3. · github.com, 7 Oct 2026
Linux: Linux packages are listed for Arch Linux, and an AppImage is available for other distributions. · github.com, 7 Oct 2026
Linux availability: Linux packages include Arch AUR options and a universal AppImage for other distributions. · github.com, 7 Oct 2026
Processing modes: It supports video upscaling through filtering and frame interpolation. · github.com, 7 Oct 2026
Processing storage: The project says processing requires no additional disk space beyond space for the final output. · github.com, 7 Oct 2026
Purpose: Video2X is a machine learning based framework for video super resolution and frame interpolation. · github.com, 7 Oct 2026
Support: The project points users to a Telegram discussion group to ask questions and talk with developers. · github.com, 7 Oct 2026
Supported models: It supports Anime4K v4, Real-ESRGAN, Real-CUGAN, and RIFE models. · github.com, 7 Oct 2026
Upscaling models: It supports Anime4K v4, Real-ESRGAN, Real-CUGAN, and custom MPV-compatible GLSL shaders. · github.com, 7 Oct 2026
Windows: The project provides a Windows installer and a graphical interface. · github.com, 7 Oct 2026
Windows release: The repository links a Windows installer and describes a GUI for Windows. · github.com, 7 Oct 2026

Where Video2X stands on Freedom251

Video Upscaling Software#22 of 40
AI Video Upscalers#19 of 32