260919-28c46a116
sinaptik-ai/pandas-ai260919-28c46a116Sep 19, 2026by lastzero
Upgrading?
AI Summary
This release significantly upgrades AI face recognition capabilities with new models and introduces support for 360-degree media, larger file sizes, and privacy controls.
Key Highlights
- New detection and embedding models improve face recognition and clustering
- Added support for 360° photos, videos, and fisheye DNG files from Insta360
- MapLibre GL JS upgraded to v6 (requires WebGL 2)
- Default file size limit raised to 5 GB for larger video indexing
- Privacy options to hide names and face regions for specific people
New Features
- 360° media viewer support
- Improved face clustering to separate people
- Private and Hidden flags for person privacy
- CLI tools for face management (migrate, reset, status)
- New config options for face recognition tuning
- Helm chart values schema validation
- Support for Cineon, ORI, and camcorder video files
- Upgraded ONNX Runtime and security libraries
Full Release Notes
This [release](https://docs.photoprism.app/release-notes/#september-19-2026) introduces new detection and embedding models for face recognition: more faces are found, including small ones in group pictures, and clustering now keeps different people apart instead of grouping them as one. Existing libraries keep their current model until you run [`photoprism faces migrate`](https://docs.photoprism.app/user-guide/ai/face-recognition/#upgrading-an-existing-library), which re-embeds every face and keeps the names you have already assigned. People whose names should remain private can now be [flagged as Private or Hidden](https://docs.photoprism.app/user-guide/organize/people/#private-hidden-people) to hide their names and face regions from non-privileged accounts, while their pictures remain visible. In addition, [360° photos, videos, and fisheye DNG files from Insta360 cameras](https://github.com/photoprism/photoprism/issues/5711) can be viewed directly, [maps have moved to MapLibre GL JS v6](https://github.com/photoprism/photoprism/issues/5812), and the [default size limit has been raised to 5 GB](https://github.com/photoprism/photoprism/issues/5824) so that larger videos are indexed without changing the configuration. A special thank you to all [our members](https://www.photoprism.app/editions/#compare) and [everyone who contributed](https://docs.photoprism.app/developer-guide/)! 🌈✨ #### What's new? - Viewer: [Added support for 360° Insta360 photos, videos, and fisheye DNG](https://github.com/photoprism/photoprism/issues/5711) by @omerdduran - AI: [Improved facial recognition with new detection and embedding models](https://github.com/photoprism/photoprism/issues/4669) by @omerdduran - AI: [Added a `Normalize` option to keep compound label names whole](https://github.com/photoprism/photoprism/issues/5773) - AI: [Upgraded ONNX Runtime from v1.26.0 to v1.29.0](https://github.com/photoprism/photoprism/issues/5703) - People: [Improved clustering to separate people whose faces were grouped as one](https://github.com/photoprism/photoprism/issues/4669) - People: [Added a confirmation before a typed name creates a new person](https://docs.photoprism.app/user-guide/organize/people/#assign-names-to-faces) - People: [Added Private and Hidden options to hide names and face regions](https://docs.photoprism.app/user-guide/organize/people/#private-hidden-people) - People: [Fixed two people being merged when reassigning a face](https://github.com/photoprism/photoprism/issues/5764) - People: [Improved error handling when updating counts](https://github.com/photoprism/photoprism/pull/5757) by @keif888 - People: [Improved memory usage and performance when naming clusters](https://github.com/photoprism/photoprism/issues/3891) - People: [Improved the speed of face updates in very large libraries](https://github.com/photoprism/photoprism/issues/5393) - Places: [Upgraded MapLibre GL JS from v5 to v6 (requires WebGL 2)](https://github.com/photoprism/photoprism/issues/5812) - Index: [Added support for Cineon, ORI, and camcorder video files](https://github.com/photoprism/photoprism/issues/5818) - Index: [Improved support for large files by raising the default size limit to 5 GB](https://github.com/photoprism/photoprism/issues/5824) - Thumbs: [Improved oversized preview requests to return the largest available size](https://github.com/photoprism/photoprism/issues/5780) - Thumbs: [Improved error messages to be logged as a single readable line](https://github.com/photoprism/photoprism/issues/5778) - Covers: [Improved album, label, and folder covers to load from the thumbs cache](https://github.com/photoprism/photoprism/issues/5779) - Metadata: [Improved the docs to include complete XMP and DCMI tags](https://www.photoprism.app/kb/metadata/) - Config: [Added a `thumb-size-face` option that limits the sources rendered for face crops](https://docs.photoprism.app/getting-started/config-options/#face-recognition) - Config: [Added a `face-cluster-core-retry` option to control the second clustering pass](https://docs.photoprism.app/getting-started/config-options/#face-recognition) - CLI: [Added `faces migrate` to switch a library to a new face model](https://docs.photoprism.app/user-guide/ai/face-recognition/#upgrading-an-existing-library) - CLI: [Added `faces reset --all` to start over without detecting faces again](https://docs.photoprism.app/user-guide/ai/face-recognition/#cli-reference) - CLI: [Added `faces status` to help with configuration and troubleshooting](https://docs.photoprism.app/user-guide/ai/face-recognition/#cli-reference) - CLI: [Added `faces subjects`, `faces ls`, and `faces markers` to inspect face data](https://docs.photoprism.app/user-guide/ai/face-recognition/#cli-reference) - CLI: [Added a Detail column showing how well a face crop was resolved](https://docs.photoprism.app/user-guide/ai/face-recognition/#cli-reference) - Helm: [Added a values schema that validates the chart configuration](https://charts.photoprism.app/) - Tests: [Improved backend and acceptance test coverage](https://github.com/photoprism/photoprism/pull/5783) by @keif888 - Security: [Upgraded `libheif` from v1.23.1 to v1.23.4 (8 CVE fixes)](https://github.com/photoprism/photoprism/issues/5814) - Security: [Upgraded Go from v1.26.5 to v1.27.1](https://github.com/golang/go/issues?q=milestone%3AGo1.27.1) - Translations: [Improved French](https://docs.photoprism.app/developer-guide/translations-weblate/) by @jean-louis67 - Translations: [Improved Hebrew](https://docs.photoprism.app/developer-guide/translations-weblate/) by @avma #### Translations Missing [user interface translations](https://docs.photoprism.app/developer-guide/translations-weblate/) have been generated with the help of DeepL and Google Translate. Native speakers are [welcome to help us improve them](https://docs.photoprism.app/developer-guide/translations-weblate/) where needed. [Learn more ›](https://docs.photoprism.app/developer-guide/translations-weblate/) #### Installation Packages The packages attached to this release are intended for experienced users and maintainers of third-party integrations only, as they [require manual configuration](https://dl.photoprism.app/pkg/linux/README.html#configuration) and [do not include tested system dependencies](https://dl.photoprism.app/pkg/linux/README.html#dependencies). Since we are unable to [provide support](https://www.photoprism.app/kb/getting-support) for custom installations, we recommend [using one of our Docker images](https://docs.photoprism.app/getting-started/docker-compose/) to run PhotoPrism on a private server or NAS device. [Learn more ›](https://dl.photoprism.app/pkg/linux/README.html)
Related Repositories
public-apis/public-apis★ 491,193
A collective list of free APIs
NousResearch/hermes-agent★ 256,048
The agent that grows with you
yt-dlp/yt-dlp★ 200,218
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,539
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,701
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.