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

41
/ 100
Emerging

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.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

553

Forks

41

Language

Kotlin

License

GPL-3.0

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.