Categories
Photo Management Semantic Search Face Recognition Self-Hosted Gallery Photo Organization AI Photo Culling Image ScoringStars
Forks
Watchers
Developer links
Facet
Thousands of frames land on the card after a wedding shoot, and Facet finds the keepers among the bursts, blinks, and near-duplicates. Facet scores every photo across nine dimensions, aesthetic quality, composition, face quality, eye sharpness, technical sharpness, color, exposure, subject saliency, and dynamic range, with category-specific weights for portraits, landscapes, wildlife, and 30-plus other content types. The culling darkroom groups bursts and visually similar frames, protects exposure brackets and panorama sequences, and flags closed eyes per face, so you keep the sharpest open-eyed frame and reject the rest in one pass. Face detection clusters into people you can rename, merge, and search, while albums, star ratings, favorites, and AI content tags organize what survives. Browse survivors through a mosaic gallery with semantic search by plain description, a timeline, a geotag map, and slideshow capsules. Statistics dashboards track your gear usage and metric correlations, and the weight editor learns from A/B comparisons so scores drift toward your own taste. Shared album links support client proofing with hearts and comments, phones auto-upload over the built-in WebDAV inbox, and ratings round-trip to Lightroom, darktable, and Immich through XMP sidecars. Everything runs locally on your own hardware: no cloud accounts, no subscriptions, no photo ever leaves the server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Keepers Found In Minutes
- Nine-dimension scoring with category-specific weights ranks every frame; Top Picks surfaces the strongest shots across a 100k-photo library without opening each file by hand.
- Bursts Collapse To Winners
- Burst, similarity, and duplicates are grouped automatically; blink and per-face eye badges pick the sharpest open-eyed frame while brackets and panorama sequences stay protected whole.
- Scores Learn Your Taste
- The per-category weight editor shows live score previews, and A/B photo comparisons teach a personal ranker from your picks, ratings, favorites, and rejects over time.
- Your Archive Stays Private
- Everything runs on your own server with no accounts or cloud uploads; Docker Compose starts the stack, and shared album links add client proofing without exposing your library.
Features
- Nine-Dimension Photo Scoring
- Aesthetic, composition, face quality, eye and technical sharpness, color, exposure, saliency, and dynamic range, weighted per content category across 30-plus types like portrait, landscape, and macro.
- Burst And Blink Culling
- Burst detection, similarity groups, scenes, and perceptual-hash duplicates with per-face blink and expression badges; genre presets tune strictness for sports, wedding, concert, or wildlife shoots.
- Face Recognition People Library
- Faces are detected, embedded, and clustered into persons you can search, rename, and merge; merge suggestions link look-alike clusters, and blinks read per person in the culling lightbox.
- Semantic Search Gallery
- Natural-language queries search photo embeddings; filters slice by person, camera, lens, tag, folder, date, or quality range, and a map view clusters geotagged shots by place.
- Lightroom XMP Interop
- Ratings, labels, keywords, captions, and face regions round-trip through XMP sidecars for Lightroom, darktable, digiKam, and Capture One, with a Lightroom plug-in and Immich rating sync.
- WebDAV Phone Auto-Upload
- PhotoSync or any WebDAV client drops phone shots into the built-in /dav inbox; watched folders score new arrivals automatically, and an MCP endpoint lets AI agents search the library.