8000 GitHub - sh-himanshu/auto-cut: Remove image backgrounds directly in your browser with multiple AI models, no data sent to any server · GitHub
[go: up one dir, main page]

Skip to content
sh-himanshuPublic

About

Remove image backgrounds directly in your browser with multiple AI models, no data sent to any server

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

Auto Cut Logo

Auto Cut

Remove image backgrounds directly in your browser — no data sent to any server.

Auto Cut Banner

Features

  • 3 AI Models — Switch between IMG.LY (fast, on-device), RMBG-1.4 (high-quality transformer, ~40 MB), and RMBG-2.0 (best quality, gated model)
  • 100% Client-Side — All processing runs locally in your browser. Images never leave your device
  • Custom Backgrounds — Replace backgrounds with transparent, solid colors, or any hex value
  • Multi-Format Export — Download as PNG, JPEG, or WEBP at full resolution with no watermarks
  • Dark & Light Theme — Smooth theme switching with system preference detection
  • Sample Images — Try it instantly with built-in sample images
  • Offline-Ready PWA — Works offline with service worker caching
  • HuggingFace Token Support — Access gated models like RMBG-2.0 with your own token

Tech Stack

Getting Started

# Install dependencies
pnpm install

# Run the development server
pnpm dev

Open http://localhost:3000 in your browser.

Scripts

Command Description
pnpm dev Start development server
pnpm build Build for production (static export)
pnpm start Start production server
pnpm lint Run ESLint
pnpm typecheck Run TypeScript type checking
pnpm format Format code with Prettier

License

MIT

Deploy on Vercel

The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.

Check out our Next.js deployment documentation for more details.

About

Remove image backgrounds directly in your browser with multiple AI models, no data sent to any server

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Contributors

Languages

0