openai/CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

60
/ 100
Established

This project helps you understand what an image depicts by matching it with descriptive text. You input an image and a list of possible text descriptions or categories, and it tells you which description is most relevant. This is ideal for anyone working with large collections of images who needs to quickly categorize, search, or understand image content without extensive manual labeling.

32,796 stars. Actively maintained with 1 commit in the last 30 days.

Use this if you need to classify images or find relevant text descriptions for images without needing to train a custom model for every new category.

Not ideal if you need to generate new descriptive text from an image or if you only need exact keyword matching for image captions.

image-categorization visual-search content-moderation digital-asset-management data-labeling-automation
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

32,796

Forks

3,961

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 18, 2026

Commits (30d)

1

Get this data via API

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

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