AI Image Toolkit that runs fully in your browser — free, private, and offline-first. Removerized is an open-source, AI-powered image toolkit designed for privacy and accessibility, running entirely within the user's browser. It offers features like background removal and image upscaling without requiring data uploads or backend servers, benefiting users who prioritize data privacy and offline functionality.

How It Works

The project leverages ONNX Runtime Web to execute AI models directly in the browser via WebAssembly (WASM). All necessary assets, including AI models, are cached locally using IndexedDB, enabling offline use after the initial load. This client-side-only architecture ensures zero data collection and processing occurs directly on the user's device.

Quick Start & Requirements

• Install/Run: pnpm install followed by pnpm dev.
• Prerequisites: Requires Node.js and pnpm.
• Resource Footprint: Designed for offline use after initial load; resource usage depends on model complexity and image size.
• Links: Live Demo (mentioned but URL not provided in README).

Highlighted Details

• Features multiple AI models for diverse image manipulation tasks.
• Provides fast, accurate, and fully local background removal.
• Includes AI-powered image upscaling capabilities.
• Supports batch processing for efficiency.
• Models are cached locally for instant reuse.
• Operates entirely client-side, ensuring privacy and offline functionality.

Maintenance & Community

Contributions, ideas, and feedback are welcomed via issues or pull requests. The project is maintained by Yoss. No specific community channels (like Discord/Slack) or roadmap links are provided in the README.

Licensing & Compatibility

Licensed under the GNU General Public License v3.0 (GPLv3). This is a strong copyleft license, meaning modifications and derivative works must also be made available under the GPLv3. Commercial use or linking with closed-source software may be restricted due to the copyleft nature of the license.

Limitations & Caveats

As a browser-based application, performance may be constrained by the user's device capabilities and browser limitations compared to native applications. Features like image colorization, photo restoration, and PWA support are listed on the roadmap, indicating they are not yet implemented.