ComfyUI-Easy-DotsOCR

ComfyUI-Easy-DotsOCR
★ 6

OCR图像文字识别ComfyUI节点易于安装
在 ComfyUI 中使用 DotsOCR 引擎对图像进行文字提取，便于将 OCR 结果并入工作流，安装与使用简单。
💡 将图片输入节点以提取文字并在工作流中使用
🍴 1 Forks💻 Python🔄 2025-10-05
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/e00a65475347
📦 requirements.txt
qwen_vl_utils
transformers>=4.51.3
📄 README

ComfyUI-Easy-DotsOCR

ComfyUI-Easy-DotsOCR is a custom node for ComfyUI that provides text extraction via the DotsOCR engine. This node enables users to extract text from images directly within ComfyUI workflows.

Installation

  • Clone this repository into your ComfyUI custom_nodes directory:

    • “`bash

    git clone https://github.com/yolain/ComfyUI-Easy-DotsOCR

    “`

  • Install required dependencies:

    • “`bash

    pip install -r requirements.txt

    “`

  • Restart ComfyUI. The DotsOCR node will be available in the node list.

    • Usage

  • Add the DotsOCR node to your ComfyUI workflow.
  • Connect an image input to the node.
  • Run the workflow to extract text from the image.

    • Download Models (Manual)

    Download All models to ComfyUI/models/LLM/dots-ocr

    Development

    This project is developed based on dots.ocr. Many core OCR functionalities are adapted from this upstream project. Please refer to their repository for more details and credits.

    File Structure

  • dots.py: Core OCR logic
  • nodes.py: ComfyUI node definitions
  • utility/: Helper functions for image and download operations
  • prompt_templates.yaml: Prompt templates for OCR tasks
  • requirements.txt: Python dependencies

    • License

    This project inherits the license from dots.ocr. Please review their license terms before use.

    Acknowledgements

  • dots.ocr for the original OCR implementation
  • ComfyUI for the node workflow framework

    • Contact

    For issues or feature requests, please open an issue on this repository.