---
license: apache-2.0
library_name: transformers
pipeline_tag: image-feature-extraction
---

# OpenVision

This repository contains the model for extracting image features as described in [OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning](https://huggingface.co/papers/2505.04601).

More information can be found on the [project page](https://ucsc-vlaa.github.io/OpenVision) and the [Github repository](https://github.com/UCSC-VLAA/OpenVision).