salesforce/LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

46
/ 100
Emerging

This helps developers and researchers integrate advanced AI models that understand both images and text into their applications. You can input images and questions, and it will generate descriptive captions or answer questions about the visuals. It's designed for AI practitioners building multimodal systems.

11,183 stars. No commits in the last 6 months.

Use this if you are an AI developer or researcher looking to quickly implement and experiment with state-of-the-art vision-language models for tasks like image captioning, visual question answering, or text-to-image generation.

Not ideal if you are an end-user without programming knowledge, as this is a library for building AI solutions, not a ready-to-use application.

visual-question-answering image-captioning multimodal-ai-development text-to-image-generation ai-model-benchmarking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

11,183

Forks

1,101

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Nov 18, 2024

Commits (30d)

0

Get this data via API

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

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