digiKam Semantic Image Search

Project information

Development fork dedicated to implementing Bug 515936. This fork focuses on adding native support for Semantic Image Search powered by multi-modal CLIP-ViT-H-14 models. This enables dual-modal text-to-image and image-to-image vector retrieval workflows within the application. Changes will be submitted upstream via Merge Request once localized benchmarking and regression testing are complete.

68,952 Commits
87 Branches
154 Tags

README
LICENSE
CHANGELOG
CONTRIBUTING

Created on

May 24, 2026

Loading