JIA-Lab-research/LISA
Project Page for "LISA: Reasoning Segmentation via Large Language Model"
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.
Stars
2,604
Forks
200
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase