FoundationVision/Groma
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
This tool helps you understand and process images by identifying specific regions mentioned in text descriptions. You input an image and a natural language query describing something in that image, and it outputs a precise bounding box or a detailed textual response grounded in the visual context. Researchers and developers working with visual-language tasks, such as creating smart image assistants or improving visual search, would use this.
584 stars. No commits in the last 6 months.
Use this if you need a multimodal AI that can accurately pinpoint specific objects or areas within an image based on a detailed text description.
Not ideal if your primary goal is general image classification or object detection without the need for language-based regional grounding.
Stars
584
Forks
45
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/FoundationVision/Groma"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TinyLLaVA/TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
zjunlp/EasyInstruct
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
rese1f/MovieChat
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
NVlabs/Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies