xemle/home-gallery

Self-hosted open-source web gallery to view your photos and videos featuring mobile-friendly, tagging and AI powered image discovery

What it solves

HomeGallery provides a private, self-hosted solution for managing and browsing large personal photo and video collections. It addresses privacy concerns associated with cloud-based storage while offering advanced discovery features like AI-powered face recognition and similar image searching that are typically only found in commercial cloud services.

How it works

It runs as a local server (via binary or Docker) that indexes your media directories. It uses a combination of local processing and an optional API server to perform computer vision tasks, such as object detection, face recognition, and reverse image lookup. The interface is a mobile-friendly web application that loads a lightweight database into the browser for fast performance, even with collections containing hundreds of thousands of files.

Who it’s for

It is designed for tech-savvy users who want to maintain full control over their media archives, prefer self-hosting over cloud services, and want a fast, searchable interface for their photos and videos on both desktop and mobile devices.

Highlights

  • AI-powered features including face detection, object recognition, and reverse image search.
  • High performance with support for large libraries (up to 400,000+ media files).
  • Privacy-focused architecture that allows for local-only processing.
  • Mobile-optimized experience via PWA support and virtual scrolling.
  • Flexible media management with support for offline storage and duplicate file detection.

Related

  • Project
    lessthanoptimal/BoofCV

    BoofCV is an open-source, real-time computer vision library written in Java that provides tools for image processing, camera calibration, and object recognition.

  • Project
    Maelic/RelateAnything

    A real-time open-vocabulary relation prediction system that identifies relationships between objects in images using custom-defined predicates without retraining.

  • Project
    Linfeng-Tang/Image-Fusion

    A comprehensive collection of research papers and code implementations for image fusion, covering multi-modal, digital photography, and remote sensing image combination techniques.

  • Project
    liliu-avril/Awesome-Segment-Anything

    A curated, community-driven repository that serves as a comprehensive survey and index of academic papers and open-source projects related to the Segment Anything Model (SAM) and its ecosystem.