---
license: apache-2.0
language:
- en
---

# SPHINX-V Model Card

## Model type:
**SPHINX-V** is a new multimodal large language model designed for visual prompting, equipped with a novel visual prompt encoder and a two-stage training strategy. SPHINX-V supports multiple visual prompts simultaneously across various types, significantly enhancing user flexibility and achieve a fine-grained and open-world understanding of visual prompts.


## Paper or resources for more information:
Project Page: [Draw-and-Understand](https://draw-and-understand.github.io/) \
Paper: [https://arxiv.org/abs/2403.20271](https://arxiv.org/abs/2403.20271) \
Code: [https://github.com/AFeng-x/Draw-and-Understand](https://github.com/AFeng-x/Draw-and-Understand) \
Dataset: [MDVP-Data & MDVP-Bench](https://huggingface.co/datasets/Afeng-x/Draw-and-Understand)


## Intended use
**Primary intended uses:**
The principal application of SPHINX-V is centered around conducting research in the realm of visual prompting large multimodal models and chatbots.

**Primary intended users:**
The model is primarily designed for use by researchers and enthusiasts specializing in fields such as computer vision, natural language processing, and interactive artificial intelligence.


## License
Llama 2 is licensed under the LLAMA 2 Community License, 
Copyright (c) Meta Platforms, Inc. All Rights Reserved.


## Citations
```
@misc{lin2024drawandunderstand,
      title={Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want}, 
      author={Weifeng Lin and Xinyu Wei and Ruichuan An and Peng Gao and Bocheng Zou and Yulin Luo and Siyuan Huang and Shanghang Zhang and Hongsheng Li},
      year={2024},
      eprint={2403.20271},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
```