slavabarkov/tidy
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine
Leverages OpenCLIP (trained on LAION-2B dataset) to encode images into a persistent local index during first launch, enabling semantic search via natural language descriptions or visual similarity without server connectivity. Supports bidirectional querying—both text-to-image and image-to-image retrieval—with automatic re-indexing of newly added photos, all executed through ONNX Runtime for on-device inference.
553 stars. No commits in the last 6 months.
Stars
553
Forks
41
Language
Kotlin
License
GPL-3.0
Category
Last pushed
Mar 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/slavabarkov/tidy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unum-cloud/UForm
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts,...
rom1504/clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
mazzzystar/Queryable
Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.
s-emanuilov/litepali
LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing,...
Ubaida-M-Yusuf/Makimus-AI
AI-powered media search — find images and videos using natural language or visual queries