Vapourkit

About

Vapourkit is a free, open-source desktop app for restoring and upscaling video on Windows and Linux. It processes videos using models and filters, with a live preview that updates as processing advances; users can adjust filters and rerun the pipeline. A side-by-side viewer compares source and output, with Video Compare built into Windows and optional on Linux. Users can queue multiple videos with custom workflows, write custom VapourSynth filters, and save or share portable .vkfilter and .vkworkflow files. Listed models include TSPAN / TFDAT VSR, AnimeJaNai, and AnimeSharpV4, and users can import their own ONNX model. Inference backends include TensorRT, DirectML, and NCNN Vulkan, depending on the system and GPU. Windows has a stable download, while Linux downloads are nightly AppImages. Linux setup creates a private Python environment under the user's configuration directory rather than installing packages globally or requiring sudo. Linux uses a curated verified filter catalog, and DirectML is Windows-only. The maker recommends at least 8 GB RAM and 6 GB VRAM.

Who it is for

Vapourkit suits people restoring or upscaling video, from straightforward processing to custom filters and queued workflows. Users should check its operating-system, GPU, and Linux setup requirements against their system.

Compared on AI video restoration software

Free plan

Yesvapourkit.app

Platform

desktopvapourkit.app

Denoising

Yesvapourkit.app

Artifact removal

Yesvapourkit.app

Frame interpolation

Yesvapourkit.app

Facts

Purpose

Vapourkit is a video restoration and upscaling app that processes videos using models and filters.vapourkit.app · 4 Oct 2026

License

The project describes Vapourkit as free and open source, with a GPL 3.0 license.github.com · 4 Oct 2026

Inference backends

The site lists TensorRT, DirectML, and NCNN Vulkan, with availability depending on operating system and GPU.vapourkit.app · 4 Oct 2026

Preview

Real-time preview shows output frames as processing advances, and users can adjust filters and rerun the pipeline.vapourkit.app · 4 Oct 2026

Comparison

The app can compare source and output side by side; Video Compare is built in on Windows and optional on Linux.vapourkit.app · 4 Oct 2026

Batch processing

Users can queue multiple videos with custom workflows.vapourkit.app · 4 Oct 2026

Custom filters

Users can write custom filters and use a platform-verified VapourSynth filter catalog, with more filters available on Windows.vapourkit.app · 4 Oct 2026

Workflow files

Users can save and share portable .vkfilter and .vkworkflow files.vapourkit.app · 4 Oct 2026

Models

The site lists TSPAN / TFDAT VSR, AnimeJaNai, and AnimeSharpV4, and supports importing a user's own ONNX model.vapourkit.app · 4 Oct 2026

Downloads

Windows has a stable download, while Linux downloads are currently nightly AppImages; stable Linux downloads are planned for Ko-fi when released.vapourkit.app · 4 Oct 2026

Platform requirements

The docs support Windows 10/11 x64 and x86_64 glibc-based Linux distributions that can run AppImage.vapourkit.app · 4 Oct 2026

Linux setup

Linux setup creates a private Python virtual environment and installs packages under the user's config directory without installing Python packages globally or requiring sudo.vapourkit.app · 4 Oct 2026

Platform limitation

DirectML is available on Windows only, and Linux uses a curated verified filter catalog rather than every filter in the Windows build.vapourkit.app · 4 Oct 2026

Support

The maker points users to Discord for help and feature requests, and says donations support development.vapourkit.app · 4 Oct 2026

Open source

The maker describes Vapourkit as free and open source, and its repository lists the GPL-3.0 license.github.com · 4 Oct 2026

AI backends

Its inference backends include TensorRT, DirectML, and NCNN Vulkan, with availability depending on operating system and GPU.vapourkit.app · 4 Oct 2026

Preview and comparison

Vapourkit offers real-time output preview and a side-by-side source and output viewer; Video Compare is built in on Windows and optional on Linux.vapourkit.app · 4 Oct 2026

Batch workflows

Users can queue multiple videos with custom workflows and save or share .vkfilter and .vkworkflow files.vapourkit.app · 4 Oct 2026

Filters

The app includes a catalog of VapourSynth filters for tasks such as deinterlacing, interpolation, restoration, denoising, sharpening, anti-aliasing, dehalo, and debanding, and supports custom filters.vapourkit.app · 4 Oct 2026

Integrations

Vapourkit uses VapourSynth, FFmpeg, and AI inference backends; Linux setup requires Python, FFmpeg/ffprobe, and Vulkan, while Video Compare is optional there.vapourkit.app · 4 Oct 2026

Privacy and local setup

Linux setup creates a private Python virtual environment under the user's configuration directory and does not install Python packages globally or require sudo.vapourkit.app · 4 Oct 2026

Platform limits

Vapourkit supports Windows 10/11 x64 and x86_64 glibc-based Linux distributions that can run the AppImage; Linux offers a curated verified filter catalog rather than the full Windows catalog.vapourkit.app · 4 Oct 2026

System requirements

The maker recommends at least 8 GB RAM and 6 GB VRAM, and Linux requires Python 3.12 or 3.13, FFmpeg/ffprobe, and a working Vulkan runtime.vapourkit.app · 4 Oct 2026

Intended users

The maker presents Vapourkit for people restoring or upscaling video, from a simple load-and-process workflow to custom filters and batch pipelines.vapourkit.app · 4 Oct 2026

Where it ranks on Inferse

• Best AI Video Restoration Software in 2026#5 of 25

Sources

• vapourkit.app/introduction/· checked 4 Oct 2026
• github.com/Kim2091/vapourkit· checked 4 Oct 2026
• vapourkit.app· checked 4 Oct 2026
• vapourkit.app/installation/· checked 4 Oct 2026
• ko-fi.com/s/2e5ebd456d· checked 4 Oct 2026