AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Photographers › removerized
✦ Free & open sourcePhotographers

removerized

Run AI background removal and image upscaling locally in your browser.

Browser-based AI image toolkit for privacy

Perform client-side background removal and upscaling with zero server uploads.

Free forever · open source · GPL-3.0
✓ Light setup✓ Browser-based✓ Real-time collaboration
6.3
ZEKAI
Local-first browser AI toolkit
Free & open source · Photographers
Ease of setup2
Usefulness7
Maintenance9.5
Community6.5
★ 1,630
GITHUB
Oct 2026
UPDATED
GPL-3.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

Removerized is an open-source AI image toolkit that executes background removal and upscaling directly inside your browser via ONNX Runtime Web. It suits photographers and creators who need strict privacy and offline capability without installing heavy desktop software.

Runs on
Web
Hosting
Self-host
Languages
TypeScript
License
GPL-3.0

What it is

The application loads AI models straight into your browser, executing inference via WebAssembly and caching assets locally in IndexedDB. It supports batch processing multiple images at once and provides advanced controls over quality, format, and output parameters.

Who it's for

It suits privacy-conscious photographers looking to process images offline without sending client work to third-party servers. It is not suitable for those who need cloud-synced workflows or enterprise-grade photo editing suites.

Key features

Local Browser AI

Runs completely offline using ONNX Runtime Web and WebAssembly.

Model Caching

Stores AI models locally in IndexedDB for instant reuse after the first load.

Batch Processing

Process multiple images simultaneously directly on your device.

Advanced Controls

Tweak output quality, format, and specific parameters for your images.

How to start

Up and running in 3 steps

1
Clone the repository to your local machine.
2
Run yarn install to set up the project dependencies.
3
Run yarn dev to launch the local development environment.
Real talk

Our honest verdict

What's great

  • Zero data collection with fully client-side processing
  • Works offline after the initial asset load
  • Caches AI models locally using IndexedDB for instant reuse
  • Handles batch processing of multiple images at once

Where it falls short

  • Relies entirely on your local browser and device performance
  • Requires Yarn to install and run the development environment
  • Contribution agreement grants the maintainer rights to relicense your code for commercial editions
Cost

Pricing & license

Removerized is free software distributed under the GPL-3.0 license, with no hosted paid tier mentioned.

Paid work

Open remote AI-training roles

766 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.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: removerized for Photographers
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure removerized for you — and train your team.
Get it done for you ↗
Questions

FAQ

Do my images get uploaded to a server?

No. All processing happens entirely inside your browser using ONNX Runtime Web.

Does it work without an internet connection?

Yes, after the initial load and model caching, it works completely offline.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Photographers — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google