[NAACL 2022]Mobile Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP)
CLIP-Finder enables semantic offline searches of images from gallery photos using natural language descriptions or the camera. Built on Apple's MobileCLIP-S0 architecture, it ensures optimal performance and accurate media retrieval.
Run Apple's Mobile-Clip model on iOS to search photos.
Detect objects in real time using open-vocabulary search, LiDAR depth sensing, and on-device natural language processing on iOS.
Real-time open-vocabulary object detection on iOS - CoreML, on-device CLIP, LiDAR depth, and a local LLM. Fully offline.
A private, local-first clipboard history manager for macOS
A Mac-native photo viewer with a local AI enhancement pipeline — folder-first browsing, vim keymap, CLIP search. No cloud, no library import, no subscription.
Card to finished photos: every face judged at full resolution, a DxO preset per setup, one window from the card to the export. Early work in progress.
Native macOS photo gallery with on-device face grouping, face search and natural-language search. Vision + ArcFace + MobileCLIP, all local.
A macOS app for cleaning a folder of images: duplicates, unreadable files and train/test leakage, plus search by description using CLIP on MLX. Everything runs on your Mac and fully offline.
To associate your repository with the clip topic, visit your repo's landing page and select "manage topics."