🎨

nvidia/LocateAnything-3B

image-text-to-text model by nvidia

🎨 Image Generation

Unknown

Hugging Face

2.7K

GitHub Stars

Jul 12, 2026

First Tracked

About

AI Summary

Nvidia's LocateAnything-3B is a Hugging Face model designed for feature extraction, boasting over 1.4 million downloads and 2,700 likes, and utilizes transformers and safetensors technology.

Hugging Face model with 1,472,194 downloads and 2,708 likes. Tags: transformers, safetensors, locateanything, feature-extraction, nvidia