JIA-Lab-research/LISA

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

45
/ 100
Emerging

This tool helps you precisely identify and outline specific objects or areas within an image based on complex, descriptive text instructions. You input an image and a detailed textual query, and it outputs a segmented image highlighting the requested parts, often with an explanation. It's ideal for visual researchers, content analysts, or anyone needing to extract specific visual information with nuanced, human-like reasoning.

2,604 stars. No commits in the last 6 months.

Use this if you need to segment parts of an image that require understanding complex instructions or real-world knowledge, beyond simple object detection.

Not ideal if your segmentation tasks are simple, fixed categories (like 'car' or 'person') and don't require advanced reasoning or contextual understanding.

image-analysis visual-search content-moderation scene-understanding digital-asset-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

2,604

Forks

200

Language

Python

License

Apache-2.0

Last pushed

Feb 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JIA-Lab-research/LISA"

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