1. Tutorial Introduction

MinerU2.5-2509-1.2B is a visual language model launched by OpenDataLab and Shanghai AI Lab in September 2025. It is designed for high-precision and high-efficiency document parsing tasks. It is the latest iteration of the MinerU series, focusing on converting complex format documents such as PDF into structured machine-readable data (such as Markdown, JSON, etc.). The related paper results are "MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing".

This tutorial uses resources for a single RTX 4090 card.

2. Project Examples

3. Operation steps

1. After starting the container, click the API address to enter the Web interface

2. Usage steps

If "Bad Gateway" is displayed, it means the model is initializing. Since the model is large, please wait about 2-3 minutes and refresh the page.

Parameter Description

• Enable formula recognition: Whether to enable formula recognition. When enabled, the system will recognize mathematical formulas in the document and convert them into LaTeX format.
• Enable table recognition: Whether to enable the table recognition function. When enabled, the system will recognize the table in the document and convert it into HTML format.
• Language: Used to specify the language of the document. It can improve the accuracy of OCR.
• orce enable OCR: Force enable OCR function.

4. Discussion

🖌️ If you see a high-quality project, please leave a message in the background to recommend it! In addition, we have also established a tutorial exchange group. Welcome friends to scan the QR code and remark [SD Tutorial] to join the group to discuss various technical issues and share application effects↓

Citation Information

The citation information for this project is as follows:

@misc{niu2025mineru25decoupledvisionlanguagemodel,
      title={MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing}, 
      author={Junbo Niu and Zheng Liu and Zhuangcheng Gu and Bin Wang and Linke Ouyang and Zhiyuan Zhao and Tao Chu and Tianyao He and Fan Wu and Qintong Zhang and Zhenjiang Jin and others},
      year={2025},
      eprint={2509.22186},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2509.22186}, 
}