1. Tutorial Introduction

The HunyuanOCR project was released by Tencent's Hunyuan team in November 2025, and the related paper results are as follows:HunyuanOCR Technical Report".

Project Overview: HunyuanOCR is a revolutionary 1B parameter end-to-end OCR model. Based on Hunyuan's native multimodal architecture, it breaks away from the cumbersome process of traditional OCR, which requires detection, recognition, and stitching, achieving the ultimate experience of "single image input, direct output." This model has achieved state-of-the-art (SOTA) results in tasks such as multilingual document parsing, LaTeX formula recognition, and complex table reconstruction.

This tutorial demonstrates computing power on the OpenBayes platform using a single RTX 5090 GPU as the demonstration resource. It combines Transformers native inference with a visual web interface built using Grado, supporting one-click testing of various OCR tasks.

2. Project Examples

3. Operation steps

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

2. Upload and recognize images on the webpage.

If "Bad Gateway" is displayed, it means the model is loading. Please wait about 2-3 minutes and then refresh the page.

Citation Information

@misc{hunyuanvisionteam2025hunyuanocrtechnicalreport,
      title={HunyuanOCR Technical Report}, 
      author={Hunyuan Vision Team and Pengyuan Lyu and Xingyu Wan and Gengluo Li and Shangpin Peng and Weinong Wang and Liang Wu and Huawen Shen and Yu Zhou and Canhui Tang and Qi Yang and Qiming Peng and Bin Luo and Hower Yang and Xinsong Zhang and Jinnian Zhang and Houwen Peng and Hongming Yang and Senhao Xie and Longsha Zhou and Ge Pei and Binghong Wu and Kan Wu and Jieneng Yang and Bochao Wang and Kai Liu and Jianchen Zhu and Jie Jiang and Linus and Han Hu and Chengquan Zhang},
      year={2025},
      journal={arXiv preprint arXiv:2511.19575},
      url={[https://arxiv.org/abs/2511.19575](https://arxiv.org/abs/2511.19575)}, 
}