Final2x
Cross-platform image super-resolution tool using PyTorch and Electron.
Scale graphics and artworks locally across Windows, macOS, and Linux.
Final2x is an Electron and PyTorch-based super-resolution application designed for graphic designers and creative artists. It provides built-in models and custom model support to upscale images directly on your local hardware.
What it is
The application processes image scaling using computer-vision models powered by PyTorch and a desktop backend. You can utilize the default built-in restoration models or load custom models via the cccv backend.
Who it's for
It suits designers and artists who need local upscaling capabilities across different operating systems without relying on cloud services. It does not suit users looking for an online web service or those unfamiliar with basic command-line tools for Linux dependencies.
Key features
Cross-platform support
Runs natively on Windows, macOS, and Linux desktops.
Custom model loading
Supports loading your own restoration and super-resolution models.
PyTorch backend
Uses PyTorch and the cccv engine for low-level vision processing.
Package manager friendly
Installable via winget or Scoop on Windows, or pip for the Linux core.
Up and running in 3 steps
Our honest verdict
What's great
- Native desktop applications for Windows, macOS, and Linux
- Ability to load custom image enhancement models
- Built-in models ready for immediate use out of the box
- Open-source Python CLI core and desktop backend separation
Where it falls short
- Linux installation requires manual setup of Python 3.10 and PyTorch 2.0
- macOS security quarantine requires running a terminal command on first launch
- Package manager versions may occasionally lag behind the latest release
Pricing & license
Free under the BSD-3-Clause licence. There are no paid hosted options mentioned in the repository, so the only cost is running it on your own hardware.
Open remote AI-training roles
767 open remote AI-training roles, updated November 14, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
Can I use my own super-resolution models?
Yes, Final2x supports loading custom models using the cccv backend.
What are the requirements for Linux installation?
You need Python >= 3.10, PyTorch >= 2.0, libomp5, and xdg-utils.
