merveenoyan/siglip

Projects based on SigLIP (Zhai et. al, 2023) and Hugging Face transformers integration 🤗

38
/ 100
Emerging

This project helps you build powerful search systems that understand both images and text. You can input a collection of images and descriptions, and it creates a searchable index. The output is the ability to find images using text queries, or discover similar images. This is ideal for anyone managing large visual archives, like digital asset managers, content creators, or researchers.

300 stars. No commits in the last 6 months.

Use this if you need to quickly find specific images or related visuals within a large dataset by using descriptive text or other images.

Not ideal if you're looking for a simple, out-of-the-box solution for basic image categorization without any customization.

digital-asset-management visual-search content-retrieval image-indexing multimodal-search
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

300

Forks

20

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Feb 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/merveenoyan/siglip"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.