Local AI background remover running entirely on your device
Fast, private, open-source background extraction across desktop and mobile
unbagrnd is a cross-platform desktop and mobile app that removes backgrounds from images locally using ONNX Runtime. It suits photographers seeking a privacy-focused alternative to cloud APIs without subscription fees or data exposure risks.
It executes IS-Net models locally via Rust bindings to generate precise alpha channels or composite images onto solid colors with drop shadows. You can process single images or entire folders in batch runs, manually brush over cutouts, and adjust edge smoothing or feathering.
It suits photographers and editors who handle sensitive image batches and prefer local processing over cloud subscriptions. It does not suit those seeking an integrated cloud-based DAM or browser-based plugin ecosystem.
Runs ONNX models directly on your device without sending image data to the cloud.
Handles multiple files in a single run with template renaming, drop shadows, and ZIP exports.
Adjusts outline shift, smoothing, and feathering live to handle complex elements like hair and fur.
Allows you to paint over imperfections with undo and restore capabilities for precise cutouts.
The software is entirely free under its MIT license with no paid tiers or API costs. The only cost is your own local device storage and processing power.
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
Only on first use to download your chosen AI model; all subsequent inferences run completely offline.
Yes, you can drop a whole folder into the window to batch process cutouts and export them as a ZIP.
Run xattr -cr /Applications/unbagrnd.app in your terminal to clear the quarantine flag caused by missing code-signing.
See Zekai first in Google