From 3f1e459d6747d1853b1995bb6df9c21a59df022d Mon Sep 17 00:00:00 2001
From: breezedeus <breezedeus@163.com>
Date: Tue, 18 Jun 2024 10:44:14 +0800
Subject: [PATCH] update docs

---
 README.md                      | 24 ++++++++++-----------
 docs/RELEASE.md                |  8 +++++++
 docs/buymeacoffee.md           |  8 +++----
 docs/command.md                |  4 ++--
 docs/contact.md                |  8 +++----
 docs/demo.md                   |  2 +-
 docs/examples.md               | 30 +++++++++++++--------------
 docs/examples_en.md            | 30 +++++++++++++--------------
 docs/index.md                  | 12 +++++------
 docs/index_en.md               |  8 ++++---
 docs/models.md                 | 38 +++++++++++++++++++---------------
 docs/requirements.txt          |  2 +-
 docs/usage.md                  | 12 +++++------
 pix2text/text_formula_ocr.py   |  6 ------
 tests/test_latex_ocr.py        |  2 +-
 tests/test_pix2text.py         | 27 +++++++++++-------------
 tests/test_text_formula_ocr.py | 18 +++++++---------
 17 files changed, 121 insertions(+), 118 deletions(-)

diff --git a/README.md b/README.md
index 9c26ebc..55236c4 100644
--- a/README.md
+++ b/README.md
@@ -34,8 +34,8 @@
 
 Major changes:
 
-* Added layout analysis and table recognition models, supporting the conversion of images with complex layouts into Markdown format. See examples: [Pix2Text Online Documentation / Examples](https://pix2text.readthedocs.io/zh/latest/examples_en/).
-* Added support for converting entire PDF files to Markdown format. See examples: [Pix2Text Online Documentation / Examples](https://pix2text.readthedocs.io/zh/latest/examples_en/).
+* Added layout analysis and table recognition models, supporting the conversion of images with complex layouts into Markdown format. See examples: [Pix2Text Online Documentation / Examples](https://pix2text.readthedocs.io/zh/stable/examples_en/).
+* Added support for converting entire PDF files to Markdown format. See examples: [Pix2Text Online Documentation / Examples](https://pix2text.readthedocs.io/zh/stable/examples_en/).
 * Enhanced the interface with more features, including adjustments to existing interface parameters.
 * Launched the [Pix2Text Online Documentation](https://pix2text.readthedocs.io).
 
@@ -56,7 +56,7 @@ See more at: [RELEASE.md](docs/RELEASE.md) .
 - **Layout Analysis Model**: [breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-layout)).
 - **Table Recognition Model**: [breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-table-rec)).
 - **Text Recognition Engine**: Supports **80+ languages** such as **English, Simplified Chinese, Traditional Chinese, Vietnamese**, etc. For English and Simplified Chinese recognition, it uses the open-source OCR tool [CnOCR](https://github.com/breezedeus/cnocr), while for other languages, it uses the open-source OCR tool [EasyOCR](https://github.com/JaidedAI/EasyOCR).
-- **Mathematical Formula Detection Model (MFD)**: Mathematical formula detection model (MFD) from [CnSTD](https://github.com/breezedeus/cnstd).
+- **Mathematical Formula Detection Model (MFD)**: [breezedeus/pix2text-mfd](https://huggingface.co/breezedeus/pix2text-mfd) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-mfd)). Implemented based on [CnSTD](https://github.com/breezedeus/cnstd).
 - **Mathematical Formula Recognition Model (MFR)**: [breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-mfr)).
 
 Several models are contributed by other open-source authors, and their contributions are highly appreciated.
@@ -65,7 +65,7 @@ Several models are contributed by other open-source authors, and their contribut
   <img src="docs/figs/arch-flow.jpg" alt="Pix2Text Arch Flow"/>
 </div>
 
-For detailed explanations, please refer to the [Pix2Text Online Documentation/Models](https://pix2text.readthedocs.io/zh/latest/models/).
+For detailed explanations, please refer to the [Pix2Text Online Documentation/Models](https://pix2text.readthedocs.io/zh/stable/models/).
 
 <br/>
 
@@ -74,12 +74,12 @@ As a Python3 toolkit, P2T may not be very user-friendly for those who are not fa
 If you're interested, feel free to add the assistant as a friend by scanning the QR code and mentioning `p2t`. The assistant will regularly invite everyone to join the group where the latest developments related to P2T tools will be announced:
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/figs/wx-qr-code.JPG" alt="Wechat-QRCode" width="300px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/figs/wx-qr-code.JPG" alt="Wechat-QRCode" width="300px"/>
 </div>
 
 The author also maintains a **Knowledge Planet** [**P2T/CnOCR/CnSTD Private Group**](https://t.zsxq.com/FEYZRJQ), where questions are answered promptly. You're welcome to join. The **knowledge planet private group** will also gradually release some private materials related to P2T/CnOCR/CnSTD, including **some unreleased models**, **discounts on purchasing premium models**, **code snippets for different application scenarios**, and answers to difficult problems encountered during use. The planet will also publish the latest research materials related to P2T/OCR/STD.
 
-For more contact method, please refer to [Contact](https://pix2text.readthedocs.io/zh/latest/contact/).
+For more contact method, please refer to [Contact](https://pix2text.readthedocs.io/zh/stable/contact/).
 
 
 ## List of Supported Languages
@@ -196,15 +196,15 @@ You can also try the **[Online Demo](https://huggingface.co/spaces/breezedeus/Pi
 
 ## Examples
 
-See: [Pix2Text Online Documentation/Examples](https://pix2text.readthedocs.io/zh/latest/examples_en/).
+See: [Pix2Text Online Documentation/Examples](https://pix2text.readthedocs.io/zh/stable/examples_en/).
 
 ## Usage
 
-See: [Pix2Text Online Documentation/Usage](https://pix2text.readthedocs.io/zh/latest/usage/).
+See: [Pix2Text Online Documentation/Usage](https://pix2text.readthedocs.io/zh/stable/usage/).
 
 ## Models
 
-See: [Pix2Text Online Documentation/Models](https://pix2text.readthedocs.io/zh/latest/models/).
+See: [Pix2Text Online Documentation/Models](https://pix2text.readthedocs.io/zh/stable/models/).
 
 ## Install
 
@@ -226,15 +226,15 @@ If the installation is slow, you can specify an installation source, such as usi
 pip install pix2text -i https://mirrors.aliyun.com/pypi/simple
 ```
 
-For more information, please refer to: [Pix2Text Online Documentation/Install](https://pix2text.readthedocs.io/zh/latest/install/).
+For more information, please refer to: [Pix2Text Online Documentation/Install](https://pix2text.readthedocs.io/zh/stable/install/).
 
 ## Command Line Tool
 
-See: [Pix2Text Online Documentation/Command Tool](https://pix2text.readthedocs.io/zh/latest/command/).
+See: [Pix2Text Online Documentation/Command Tool](https://pix2text.readthedocs.io/zh/stable/command/).
 
 ## HTTP Service
 
-See: [Pix2Text Online Documentation/Command Tool/Start Service](https://pix2text.readthedocs.io/zh/latest/command/).
+See: [Pix2Text Online Documentation/Command Tool/Start Service](https://pix2text.readthedocs.io/zh/stable/command/).
 
 
 ## MacOS Desktop Application
diff --git a/docs/RELEASE.md b/docs/RELEASE.md
index a199654..dd1ac95 100644
--- a/docs/RELEASE.md
+++ b/docs/RELEASE.md
@@ -1,5 +1,13 @@
 # Release Notes
 
+## Update 2024.06.17：**V1.1.1** Released
+
+主要变更：
+
+* 数学公式检测模型（MFD）更新，检测精度获得较大提升。
+* 修复 bugs。
+
+
 ## Update 2024.06.17：**V1.1.0.7** Released
 
 Major changes:
diff --git a/docs/buymeacoffee.md b/docs/buymeacoffee.md
index dfb7ced..308d452 100644
--- a/docs/buymeacoffee.md
+++ b/docs/buymeacoffee.md
@@ -9,11 +9,11 @@ By supporting my projects through a donation, you can be a part of this journey
 
 ## 1. 知识星球
 
-欢迎加入**知识星球** **[CnOCR/CnSTD私享群](https://t.zsxq.com/FEYZRJQ)**。**知识星球私享群**会陆续发布一些 CnOCR/CnSTD/P2T 相关的私有资料。
-关于星球的更详细说明请参考：[知识星球 | Breezedeus.com](https://www.breezedeus.com/article/zsxq)。
+欢迎加入**知识星球** **[P2T/CnOCR/CnSTD私享群](https://t.zsxq.com/FEYZRJQ)**。**知识星球私享群**会陆续发布一些 CnOCR/CnSTD/P2T 相关的私有资料。
+关于星球会员享受福利的更详细说明请参考：[知识星球 | Breezedeus.com](https://www.breezedeus.com/article/zsxq)。
 
 <figure markdown>
-![知识星球二维码](https://cnocr.readthedocs.io/zh/latest/cnocr-zsxq.jpeg){: style="width:280px"}
+![知识星球二维码](https://cnocr.readthedocs.io/zh/stable/cnocr-zsxq.jpeg){: style="width:280px"}
 </figure>
 
 
@@ -23,7 +23,7 @@ By supporting my projects through a donation, you can be a part of this journey
 Give the author a reward through Alipay.
 
 <figure markdown>
-![支付宝收款码](https://cnocr.readthedocs.io/zh/latest/cnocr-zfb.jpg){: style="width:280px"}
+![支付宝收款码](https://cnocr.readthedocs.io/zh/stable/cnocr-zfb.jpg){: style="width:280px"}
 </figure>
 
 
diff --git a/docs/command.md b/docs/command.md
index de027de..b33197c 100644
--- a/docs/command.md
+++ b/docs/command.md
@@ -53,7 +53,7 @@ p2t predict -l en,ch_sim --resized-shape 768 --file-type pdf -i docs/examples/te
 预测时也支持使用自定义的参数或模型。例如，使用自定义的模型进行预测：
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --rec-kwargs '{"page_numbers": [0, 1]}' --resized-shape 768 --file-type pdf -i docs/examples/test-doc.pdf -o output-md --save-debug-res output-debug
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --rec-kwargs '{"page_numbers": [0, 1]}' --resized-shape 768 --file-type pdf -i docs/examples/test-doc.pdf -o output-md --save-debug-res output-debug
 ```
 
 
@@ -99,7 +99,7 @@ p2t serve -l en,ch_sim -H 0.0.0.0 -p 8503
 服务开启时也支持使用自定义的参数或模型。例如，使用自定义的模型进行预测：
 
 ```bash
-p2t serve -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' -H 0.0.0.0 -p 8503
+p2t serve -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' -H 0.0.0.0 -p 8503
 ```
 
 ### 服务调用
diff --git a/docs/contact.md b/docs/contact.md
index 1f28a1f..2000a8a 100644
--- a/docs/contact.md
+++ b/docs/contact.md
@@ -5,7 +5,7 @@
 ## 一、知识星球 [**P2T/CnOCR/CnSTD私享群**](https://t.zsxq.com/FEYZRJQ) 
 
 作者维护 **知识星球** [**P2T/CnOCR/CnSTD私享群**](https://t.zsxq.com/FEYZRJQ) ，欢迎加入。**知识星球私享群**会陆续发布一些 P2T/CnOCR/CnSTD 相关的私有资料。
-关于星球的更详细说明请参考：[知识星球 | Breezedeus.com](https://www.breezedeus.com/article/zsxq)。
+关于星球会员享受福利的更详细说明请参考：[知识星球 | Breezedeus.com](https://www.breezedeus.com/article/zsxq)。
 
 <figure markdown>
 ![知识星球二维码](https://cnocr.readthedocs.io/zh/latest/cnocr-zsxq.jpeg){: style="width:280px"}
@@ -20,14 +20,14 @@
 ![微信交流群](https://huggingface.co/datasets/breezedeus/cnocr-wx-qr-code/resolve/main/wx-qr-code.JPG){: style="width:270px"}
 </figure>
 
-正常情况小助手会定期邀请入群，但无法保证时间。如果期望尽快得到答复，可以加入上面的知识星球 [**CnOCR/CnSTD私享群**](https://t.zsxq.com/FEYZRJQ) 。
+正常情况小助手会定期邀请入群，但无法保证时间。如果期望尽快得到答复，可以加入上面的知识星球 [**P2T/CnOCR/CnSTD私享群**](https://t.zsxq.com/FEYZRJQ) 。
 
 
 ## 三、Discord
 
-欢迎加入 [**我的Discord 服务器**](https://discord.gg/GgD87WM8Tf) 。
+欢迎加入 [**Pix2Text Discord 服务器**](https://discord.gg/GgD87WM8Tf) 。
 
-Welcome to join [**my Discord Server**](https://discord.gg/GgD87WM8Tf) .
+Welcome to join [**Pix2Text Discord Server**](https://discord.gg/GgD87WM8Tf) .
 
 
 ## 四、邮件 / Email
diff --git a/docs/demo.md b/docs/demo.md
index f55b70e..95b43e7 100644
--- a/docs/demo.md
+++ b/docs/demo.md
@@ -11,7 +11,7 @@
 
 ## 在线 Demo 🤗
 
-也可以使用 **[在线 Demo](https://huggingface.co/spaces/breezedeus/Pix2Text-Demo)**（无法科学上网可以使用 [国内 Demo](https://hf-mirror.com/spaces/breezedeus/Pix2Text-Demo)） 尝试 **P2T** 在不同语言上的效果。但在线 Demo 使用的硬件配置较低，速度会较慢。如果是简体中文或者英文图片，建议使用 **[P2T网页版](https://p2t.breezedeus.com)**。
+也可以使用 **[在线 Demo](https://huggingface.co/spaces/breezedeus/Pix2Text-Demo)**（无法科学上网可以使用 [国内镜像](https://hf.qhduan.com/spaces/breezedeus/Pix2Text-Demo)） 尝试 **P2T** 在不同语言上的效果。但在线 Demo 使用的硬件配置较低，速度会较慢。如果是简体中文或者英文图片，建议使用 **[P2T网页版](https://p2t.breezedeus.com)**。
 
 <figure markdown>
 ![在线 Demo](https://pic3.zhimg.com/80/v2-ebe8d3d955a580a297aabcd27439604e_720w.webp)
diff --git a/docs/examples.md b/docs/examples.md
index 21a5d32..c9104ed 100644
--- a/docs/examples.md
+++ b/docs/examples.md
@@ -23,7 +23,7 @@ doc.to_markdown('output-md')  # 导出的 Markdown 信息保存在 output-md 目
 也可以使用命令行完成一样的功能，如下面命令使用了付费版模型（MFD + MFR + CnOCR 三个付费模型）进行识别：
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --rec-kwargs '{"page_numbers": [0, 1]}' --resized-shape 768 --file-type pdf -i docs/examples/test-doc.pdf -o output-md --save-debug-res output-debug
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --rec-kwargs '{"page_numbers": [0, 1]}' --resized-shape 768 --file-type pdf -i docs/examples/test-doc.pdf -o output-md --save-debug-res output-debug
 ```
 
 识别结果见 [output-md/output.md](output-md/output.md)。
@@ -36,7 +36,7 @@ p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Us
 可以使用函数 `.recognize_page()` 识别图片中的文字和数学公式。如针对以下图片 ([examples/page2.png](examples/page2.png))：
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/page2.png" alt="Page-image" width="600px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/page2.png" alt="Page-image" width="600px"/>
 </div>
 
 调用方式如下：
@@ -53,7 +53,7 @@ page.to_markdown('output-page')  # 导出的 Markdown 信息保存在 output-pag
 也可以使用命令行完成一样的功能，如下面命令使用了付费版模型（MFD + MFR + CnOCR 三个付费模型）进行识别：
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type page -i docs/examples/page2.png -o output-page --save-debug-res output-debug-page
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type page -i docs/examples/page2.png -o output-page --save-debug-res output-debug-page
 ```
 
 识别结果和 [output-md/output.md](output-md/output.md) 类似。
@@ -64,7 +64,7 @@ p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Us
 可以使用函数 `.recognize_text_formula()` 识别图片中的文字和数学公式。如针对以下图片 ([examples/en1.jpg](examples/en1.jpg))：
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/en1.jpg" alt="English-mixed-image" width="600px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/en1.jpg" alt="English-mixed-image" width="600px"/>
 </div>
 
 调用方式如下：
@@ -83,13 +83,13 @@ print(outs)
 也可以使用命令行完成一样的功能，如下面命令使用了付费版模型（MFD + MFR + CnOCR 三个付费模型）进行识别：
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg --save-debug-res out-debug-en1.jpg
 ```
 
 或者使用免费开源模型进行识别：
 
 ```bash
-p2t predict -l en,ch_sim --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
+p2t predict -l en,ch_sim --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg --save-debug-res out-debug-en1.jpg
 ```
 
 ## 识别纯公式图片
@@ -97,7 +97,7 @@ p2t predict -l en,ch_sim --resized-shape 768 --file-type text_formula -i docs/ex
 对于只包含数学公式的图片，使用函数 `.recognize_formula()` 可以把数学公式识别为 LaTeX 表达式。如针对以下图片 ([examples/math-formula-42.png](examples/math-formula-42.png))：
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/math-formula-42.png" alt="Pure-Math-Formula-image" width="300px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/math-formula-42.png" alt="Pure-Math-Formula-image" width="300px"/>
 </div>
 
 
@@ -123,7 +123,7 @@ p2t predict -l en,ch_sim --formula-ocr-config '{"model_name":"mfr-pro","model_ba
 或者使用免费开源模型进行识别：
 
 ```bash
-p2t predict -l en,ch_sim --file-type textformula -i docs/examples/math-formula-42.png
+p2t predict -l en,ch_sim --file-type formula -i docs/examples/math-formula-42.png
 ```
 
 ## 识别纯文字图片
@@ -131,7 +131,7 @@ p2t predict -l en,ch_sim --file-type textformula -i docs/examples/math-formula-4
 对于只包含文字不包含数学公式的图片，使用函数 `.recognize_text()` 可以识别出图片中的文字。此时 Pix2Text 相当于一般的文字 OCR 引擎。如针对以下图片 ([examples/general.jpg](examples/general.jpg))：
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/general.jpg" alt="Pure-Math-Formula-image" width="400px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/general.jpg" alt="Pure-Math-Formula-image" width="400px"/>
 </div>
 
 
@@ -151,13 +151,13 @@ print(outs)
 也可以使用命令行完成一样的功能，如下面命令使用了付费版模型（CnOCR 一个付费模型）进行识别：
 
 ```bash
-p2t predict -l en,ch_sim --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --file-type text -i docs/examples/general.jpg
+p2t predict -l en,ch_sim --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --file-type text --no-return-text -i docs/examples/general.jpg --save-debug-res out-debug-general.jpg
 ```
 
 或者使用免费开源模型进行识别：
 
 ```bash
-p2t predict -l en,ch_sim --file-type text -i docs/examples/general.jpg
+p2t predict -l en,ch_sim --file-type text --no-return-text -i docs/examples/general.jpg --save-debug-res out-debug-general.jpg
 ```
 
 
@@ -172,7 +172,7 @@ p2t predict -l en,ch_sim --file-type text -i docs/examples/general.jpg
 **识别命令**：
 
 ```bash
-p2t predict -l en --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
+p2t predict -l en --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
 ```
 
 ### 简体中文
@@ -184,7 +184,7 @@ p2t predict -l en --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/kin
 **识别命令**：
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/mixed.jpg
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/mixed.jpg --save-debug-res out-debug-mixed.jpg
 ```
 
 ### 繁体中文
@@ -196,7 +196,7 @@ p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Us
 **识别命令**：
 
 ```bash
-p2t predict -l en,ch_tra --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/ch_tra.jpg
+p2t predict -l en,ch_tra --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/ch_tra.jpg --save-debug-res out-debug-tra.jpg
 ```
 
 > 注意 ⚠️ ：请通过以下命令安装 pix2text 的多语言版本：
@@ -213,7 +213,7 @@ p2t predict -l en,ch_tra --mfd-config '{"model_type": "yolov7", "model_fp": "/Us
 **识别命令**：
 
 ```bash
-p2t predict -l en,vi --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 768 --no-auto-line-break --file-type text_formula -i docs/examples/vietnamese.jpg
+p2t predict -l en,vi --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 608 --no-auto-line-break --file-type text_formula -i docs/examples/vietnamese.jpg --save-debug-res out-debug-vi.jpg
 ```
 
 > 注意 ⚠️ ：请通过以下命令安装 pix2text 的多语言版本：
diff --git a/docs/examples_en.md b/docs/examples_en.md
index 9ee94a0..ba67e18 100644
--- a/docs/examples_en.md
+++ b/docs/examples_en.md
@@ -23,7 +23,7 @@ doc.to_markdown('output-md')  # The exported Markdown information is saved in th
 You can also achieve the same functionality using the command line. Below is a command that uses the premium models (MFD + MFR + CnOCR) for recognition:
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --rec-kwargs '{"page_numbers": [0, 1]}' --resized-shape 768 --file-type pdf -i docs/examples/test-doc.pdf -o output-md --save-debug-res output-debug
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --rec-kwargs '{"page_numbers": [0, 1]}' --resized-shape 768 --file-type pdf -i docs/examples/test-doc.pdf -o output-md --save-debug-res output-debug
 ```
 
 You can find the recognition result in [output-md/output.md](output-md/output.md).
@@ -37,7 +37,7 @@ You can find the recognition result in [output-md/output.md](output-md/output.md
 You can use the `.recognize_page()` function to recognize text and mathematical formulas in images. For example, for the following image ([examples/page2.png](examples/page2.png)):
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/page2.png" alt="Page-image" width="600px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/page2.png" alt="Page-image" width="600px"/>
 </div>
 
 You can call the function like this:
@@ -54,7 +54,7 @@ page.to_markdown('output-page')  # The exported Markdown information is saved in
 You can also achieve the same functionality using the command line. Below is a command that uses the premium models (MFD + MFR + CnOCR) for recognition:
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type page -i docs/examples/page2.png -o output-page --save-debug-res output-debug-page
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type page -i docs/examples/page2.png -o output-page --save-debug-res output-debug-page
 ```
 
 The recognition result is similar to [output-md/output.md](output-md/output.md).
@@ -65,7 +65,7 @@ The recognition result is similar to [output-md/output.md](output-md/output.md).
 For paragraph images containing both formulas and texts, you don't need to use the layout analysis model. You can use the `.recognize_text_formula()` function to recognize both texts and mathematical formulas in the image. For example, for the following image ([examples/en1.jpg](examples/en1.jpg)):
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/en1.jpg" alt="English-mixed-image" width="600px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/en1.jpg" alt="English-mixed-image" width="600px"/>
 </div>
 
 You can call the function like this:
@@ -84,13 +84,13 @@ The returned result `outs` is a dictionary, where the key `position` represents
 You can also achieve the same functionality using the command line. Below is a command that uses the premium models (MFD + MFR + CnOCR) for recognition:
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg --save-debug-res out-debug-en1.jpg
 ```
 
 Or use the free open-source models for recognition:
 
 ```bash
-p2t predict -l en,ch_sim --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
+p2t predict -l en,ch_sim --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg --save-debug-res out-debug-en1.jpg
 ```
 
 ## Recognize Pure Formula Images
@@ -98,7 +98,7 @@ p2t predict -l en,ch_sim --resized-shape 768 --file-type text_formula -i docs/ex
 For images containing only mathematical formulas, you can use the `.recognize_formula()` function to recognize the formulas as LaTeX expressions. For example, for the following image ([examples/math-formula-42.png](examples/math-formula-42.png)):
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/math-formula-42.png" alt="Pure-Math-Formula-image" width="300px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/math-formula-42.png" alt="Pure-Math-Formula-image" width="300px"/>
 </div>
 
 You can call the function like this:
@@ -123,7 +123,7 @@ p2t predict -l en,ch_sim --formula-ocr-config '{"model_name":"mfr-pro","model_ba
 Or use the free open-source model for recognition:
 
 ```bash
-p2t predict -l en,ch_sim --file-type textformula -i docs/examples/math-formula-42.png
+p2t predict -l en,ch_sim --file-type formula -i docs/examples/math-formula-42.png
 ```
 
 ## Recognize Pure Text Images
@@ -131,7 +131,7 @@ p2t predict -l en,ch_sim --file-type textformula -i docs/examples/math-formula-4
 For images containing only text without mathematical formulas, you can use the `.recognize_text()` function to recognize the text in the image. In this case, Pix2Text acts as a general text OCR engine. For example, for the following image ([examples/general.jpg](examples/general.jpg)):
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/examples/general.jpg" alt="Pure-Math-Formula-image" width="400px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/examples/general.jpg" alt="Pure-Math-Formula-image" width="400px"/>
 </div>
 
 You can call the function like this:
@@ -150,13 +150,13 @@ The returned result is a string representing the corresponding text sequence. Fo
 You can also achieve the same functionality using the command line. Below is a command that uses the premium model (CnOCR) for recognition:
 
 ```bash
-p2t predict -l en,ch_sim --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --file-type text -i docs/examples/general.jpg
+p2t predict -l en,ch_sim --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --file-type text --no-return-text -i docs/examples/general.jpg --save-debug-res out-debug-general.jpg
 ```
 
 Or use the free open-source model for recognition:
 
 ```bash
-p2t predict -l en,ch_sim --file-type text -i docs/examples/general.jpg
+p2t predict -l en,ch_sim --file-type text --no-return-text -i docs/examples/general.jpg --save-debug-res out-debug-general.jpg
 ```
 
 ## For Different Languages
@@ -170,7 +170,7 @@ p2t predict -l en,ch_sim --file-type text -i docs/examples/general.jpg
 **Recognition Command**:
 
 ```bash
-p2t predict -l en --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
+p2t predict -l en --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --file-type text_formula -i docs/examples/en1.jpg
 ```
 
 ### Simplified Chinese
@@ -182,7 +182,7 @@ p2t predict -l en --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/kin
 **Recognition Command**:
 
 ```bash
-p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/mixed.jpg
+p2t predict -l en,ch_sim --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --text-ocr-config '{"rec_model_name": "doc-densenet_lite_666-gru_large"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/mixed.jpg --save-debug-res out-debug-mixed.jpg
 ```
 
 ### Traditional Chinese
@@ -194,7 +194,7 @@ p2t predict -l en,ch_sim --mfd-config '{"model_type": "yolov7", "model_fp": "/Us
 **Recognition Command**:
 
 ```bash
-p2t predict -l en,ch_tra --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/ch_tra.jpg
+p2t predict -l en,ch_tra --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 768 --auto-line-break --file-type text_formula -i docs/examples/ch_tra.jpg --save-debug-res out-debug-tra.jpg
 ```
 
 > Note ⚠️: Please install the multilingual version of pix2text using the following command:
@@ -211,7 +211,7 @@ p2t predict -l en,ch_tra --mfd-config '{"model_type": "yolov7", "model_fp": "/Us
 **Recognition Command**:
 
 ```bash
-p2t predict -l en,vi --mfd-config '{"model_type": "yolov7", "model_fp": "/Users/king/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 768 --no-auto-line-break --file-type text_formula -i docs/examples/vietnamese.jpg
+p2t predict -l en,vi --mfd-config '{"model_name": "mfd-pro", "model_backend": "onnx"}' --formula-ocr-config '{"model_name":"mfr-pro","model_backend":"onnx"}' --resized-shape 608 --no-auto-line-break --file-type text_formula -i docs/examples/vietnamese.jpg --save-debug-res out-debug-vi.jpg
 ```
 
 > Note ⚠️: Please install the multilingual version of pix2text using the following command:
diff --git a/docs/index.md b/docs/index.md
index bf1b224..3428fd3 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -29,11 +29,11 @@
 
 **Pix2Text (P2T)** 整合了以下模型：
 
-- **版面分析模型**：[breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) （[国内地址](https://hf-mirror.com/breezedeus/pix2text-layout)）。
-- **表格识别模型**：[breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) （[国内地址](https://hf-mirror.com/breezedeus/pix2text-table-rec)）。
+- **版面分析模型**：[breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-layout)）。
+- **表格识别模型**：[breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-table-rec)）。
 - **文字识别引擎**：支持 **`80+` 种语言**，如**英文、简体中文、繁体中文、越南语**等。其中，**英文**和**简体中文**识别使用的是开源 OCR 工具 [CnOCR](https://github.com/breezedeus/cnocr) ，其他语言的识别使用的是开源 OCR 工具 [EasyOCR](https://github.com/JaidedAI/EasyOCR) 。
-- **数学公式检测模型（MFD）**：来自 [CnSTD](https://github.com/breezedeus/cnstd) 的数学公式检测模型（MFD）。
-- **数学公式识别模型（MFR）**：[breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) （[国内地址](https://hf-mirror.com/breezedeus/pix2text-mfr)）。
+- **数学公式检测模型（MFD）**：[breezedeus/pix2text-mfd](https://huggingface.co/breezedeus/pix2text-mfd) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-mfd)）。基于 [CnSTD](https://github.com/breezedeus/cnstd) 实现。
+- **数学公式识别模型（MFR）**：[breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-mfr)）。
 
 其中多个模型来自其他开源作者， 非常感谢他们的贡献。
 
@@ -167,7 +167,7 @@ Pix2Text 的文字识别引擎支持 **`80+` 种语言**，如**英文、简体
 
 ## 在线 Demo 🤗
 
-也可以使用 **[在线 Demo](https://huggingface.co/spaces/breezedeus/Pix2Text-Demo)**（无法科学上网可以使用 [在线 Demo](https://hf-mirror.com/spaces/breezedeus/Pix2Text-Demo)） 尝试 **P2T** 在不同语言上的效果。但在线 Demo 使用的硬件配置较低，速度会较慢。如果是简体中文或者英文图片，建议使用 **[P2T网页版](https://p2t.breezedeus.com)**。
+也可以使用 **[在线 Demo](https://huggingface.co/spaces/breezedeus/Pix2Text-Demo)**（无法科学上网可以使用 [在线 Demo](https://hf.qhduan.com/spaces/breezedeus/Pix2Text-Demo)） 尝试 **P2T** 在不同语言上的效果。但在线 Demo 使用的硬件配置较低，速度会较慢。如果是简体中文或者英文图片，建议使用 **[P2T网页版](https://p2t.breezedeus.com)**。
 
 
 ## 安装
@@ -192,7 +192,7 @@ pip install pix2text -i https://mirrors.aliyun.com/pypi/simple
 
 如果是初次使用**OpenCV**，那估计安装都不会很顺利，bless。
 
-**Pix2Text** 主要依赖 [**CnSTD>=1.2.1**](https://github.com/breezedeus/cnstd)、[**CnOCR>=2.2.2.1**](https://github.com/breezedeus/cnocr) ，以及 [**transformers>=4.37.0**](https://github.com/huggingface/transformers) 。如果安装过程遇到问题，也可参考它们的安装说明文档。
+**Pix2Text** 主要依赖 [**CnSTD>=1.2.4**](https://github.com/breezedeus/cnstd)、[**CnOCR>=2.3**](https://github.com/breezedeus/cnocr) ，以及 [**transformers>=4.37.0**](https://github.com/huggingface/transformers) 。如果安装过程遇到问题，也可参考它们的安装说明文档。
 
 > **Warning**
 >
diff --git a/docs/index_en.md b/docs/index_en.md
index 7659176..7f0577c 100644
--- a/docs/index_en.md
+++ b/docs/index_en.md
@@ -31,7 +31,7 @@
 - **Layout Analysis Model**: [breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-layout)).
 - **Table Recognition Model**: [breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-table-rec)).
 - **Text Recognition Engine**: Supports **80+ languages** such as **English, Simplified Chinese, Traditional Chinese, Vietnamese**, etc. For English and Simplified Chinese recognition, it uses the open-source OCR tool [CnOCR](https://github.com/breezedeus/cnocr), while for other languages, it uses the open-source OCR tool [EasyOCR](https://github.com/JaidedAI/EasyOCR).
-- **Mathematical Formula Detection Model (MFD)**: Mathematical formula detection model (MFD) from [CnSTD](https://github.com/breezedeus/cnstd).
+- **Mathematical Formula Detection Model (MFD)**: [breezedeus/pix2text-mfd](https://huggingface.co/breezedeus/pix2text-mfd) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-mfd)). Implemented based on [CnSTD](https://github.com/breezedeus/cnstd).
 - **Mathematical Formula Recognition Model (MFR)**: [breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) ([Mirror](https://hf-mirror.com/breezedeus/pix2text-mfr)).
 
 Several models are contributed by other open-source authors, and their contributions are highly appreciated. 
@@ -44,10 +44,12 @@ For detailed explanations, please refer to the [Models](models.md).
 
 As a Python3 toolkit, P2T may not be very user-friendly for those who are not familiar with Python. Therefore, we also provide a **[free-to-use P2T Online Web](https://p2t.breezedeus.com)**, where you can directly upload images and get P2T parsing results. The web version uses the latest models, resulting in better performance compared to the open-source models.
 
-If you're interested, feel free to add the assistant as a friend by scanning the QR code and mentioning `p2t`. The assistant will regularly invite everyone to join the group where the latest developments related to P2T tools will be announced:
+Welcome to join [**Pix2Text Discord Server**](https://discord.gg/GgD87WM8Tf), if you have any questions or suggestions.
+
+If you're interested, feel free to add the WeChat assistant as a friend by scanning the QR code and mentioning `p2t`. The assistant will regularly invite everyone to join the group where the latest developments related to P2T tools will be announced:
 
 <div align="center">
-  <img src="https://pix2text.readthedocs.io/zh/latest/figs/wx-qr-code.JPG" alt="Wechat-QRCode" width="300px"/>
+  <img src="https://pix2text.readthedocs.io/zh/stable/figs/wx-qr-code.JPG" alt="Wechat-QRCode" width="300px"/>
 </div>
 
 The author also maintains a **Knowledge Planet** [**P2T/CnOCR/CnSTD Private Group**](https://t.zsxq.com/FEYZRJQ), where questions are answered promptly. You're welcome to join. The **knowledge planet private group** will also gradually release some private materials related to P2T/CnOCR/CnSTD, including **some unreleased models**, **discounts on purchasing premium models**, **code snippets for different application scenarios**, and answers to difficult problems encountered during use. The planet will also publish the latest research materials related to P2T/OCR/STD.
diff --git a/docs/models.md b/docs/models.md
index bdc2042..08ddbe3 100644
--- a/docs/models.md
+++ b/docs/models.md
@@ -2,11 +2,11 @@
 
 **Pix2Text (P2T)** 整合了很多不同功能的模型，主要包括：
 
-- **版面分析模型**：[breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) （[国内地址](https://hf-mirror.com/breezedeus/pix2text-layout)）。
-- **表格识别模型**：[breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) （[国内地址](https://hf-mirror.com/breezedeus/pix2text-table-rec)）。
+- **版面分析模型**：[breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-layout)）。
+- **表格识别模型**：[breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-table-rec)）。
 - **文字识别引擎**：支持 **`80+` 种语言**，如**英文、简体中文、繁体中文、越南语**等。其中，**英文**和**简体中文**识别使用的是开源 OCR 工具 [CnOCR](https://github.com/breezedeus/cnocr) ，其他语言的识别使用的是开源 OCR 工具 [EasyOCR](https://github.com/JaidedAI/EasyOCR) 。
-- **数学公式检测模型（MFD）**：来自 [CnSTD](https://github.com/breezedeus/cnstd) 的数学公式检测模型（MFD）。
-- **数学公式识别模型（MFR）**：[breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) （[国内地址](https://hf-mirror.com/breezedeus/pix2text-mfr)）。
+- **数学公式检测模型（MFD）**：[breezedeus/pix2text-mfd](https://huggingface.co/breezedeus/pix2text-mfd) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-mfd)）。基于 [CnSTD](https://github.com/breezedeus/cnstd) 实现。
+- **数学公式识别模型（MFR）**：[breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) （[国内镜像](https://hf-mirror.com/breezedeus/pix2text-mfr)）。
 
 其中多个模型来自其他开源作者， 非常感谢他们的贡献。
 
@@ -22,24 +22,28 @@
 下面的说明主要针对免费的基础模型。
 
 ## 版面分析模型
-**版面分析模型** 下载地址：[breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) （不能科学上网请使用 [国内地址](https://hf-mirror.com/breezedeus/pix2text-layout)）。
+**版面分析模型** 下载地址：[breezedeus/pix2text-layout](https://huggingface.co/breezedeus/pix2text-layout) （不能科学上网请使用 [国内镜像](https://hf-mirror.com/breezedeus/pix2text-layout)）。
 把这里面的所有文件都下载到 `~/.pix2text/1.1/layout-parser` （Windows 系统放在 `C:\Users\<username>\AppData\Roaming\pix2text\1.1\layout-parser`）目录下即可，目录不存在的话请自己创建。
 
 > 注：上面路径的 `1.1` 是 pix2text 的版本号，`1.1.*` 都对应 `1.1`。如果是其他版本请自行替换。
 
 ## 表格识别模型
-**表格识别模型** 下载地址：[breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) （不能科学上网请使用 [国内地址](https://hf-mirror.com/breezedeus/pix2text-table-rec)）。
+**表格识别模型** 下载地址：[breezedeus/pix2text-table-rec](https://huggingface.co/breezedeus/pix2text-table-rec) （不能科学上网请使用 [国内镜像](https://hf-mirror.com/breezedeus/pix2text-table-rec)）。
 把这里面的所有文件都下载到 `~/.pix2text/1.1/table-rec` （Windows 系统放在 `C:\Users\<username>\AppData\Roaming\pix2text\1.1\table-rec`）目录下即可，目录不存在的话请自己创建。
 
 > 注：上面路径的 `1.1` 是 pix2text 的版本号，`1.1.*` 都对应 `1.1`。如果是其他版本请自行替换。
 
-## 数学公式检测模型
+## 数学公式检测模型（MFD）
+### `pix2text >= 1.1.1`
+Pix2Text 自 **V1.1.1** 开始，**数学公式检测模型** 下载地址：[breezedeus/pix2text-mfd](https://huggingface.co/breezedeus/pix2text-mfd) （不能科学上网请使用 [国内镜像](https://hf-mirror.com/breezedeus/pix2text-mfd)）。
+
+### `pix2text < 1.1.1`
 **数学公式检测模型**（MFD）来自 [CnSTD](https://github.com/breezedeus/cnstd) 的数学公式检测模型（MFD），请参考其代码库说明。
 
 如果系统无法自动成功下载模型文件，则需要手动从 [**cnstd-cnocr-models**](https://huggingface.co/breezedeus/cnstd-cnocr-models) （[国内镜像](https://hf-mirror.com/breezedeus/cnstd-cnocr-models)）项目中下载，或者从[百度云盘](https://pan.baidu.com/s/1zDMzArCDrrXHWL0AWxwYQQ?pwd=nstd)（提取码为 `nstd`）下载对应的zip文件并把它存放于 `~/.cnstd/1.2`（Windows下为 `C:\Users\<username>\AppData\Roaming\cnstd\1.2`）目录中。
 
-## 数学公式识别模型
-**数学公式识别模型** 下载地址：[breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) （不能科学上网请使用 [国内地址](https://hf-mirror.com/breezedeus/pix2text-mfr)）。
+## 数学公式识别模型（MFR）
+**数学公式识别模型** 下载地址：[breezedeus/pix2text-mfr](https://huggingface.co/breezedeus/pix2text-mfr) （不能科学上网请使用 [国内镜像](https://hf-mirror.com/breezedeus/pix2text-mfr)）。
 把这里面的所有文件都下载到 `~/.pix2text/1.1/mfr-onnx` （Windows 系统放在 `C:\Users\<username>\AppData\Roaming\pix2text\1.1\mfr-onnx`）目录下即可，目录不存在的话请自己创建。
 
 > 注：上面路径的 `1.1` 是 pix2text 的版本号，`1.1.*` 都对应 `1.1`。如果是其他版本请自行替换。
@@ -77,14 +81,14 @@ EasyOCR 模型下载请参考 [EasyOCR](https://github.com/JaidedAI/EasyOCR)。
 
 **模型购买地址**：
 
-| 模型名称         | 购买地址                                          | 说明 
-|--------------|-----------------------------------------------|-----------------------------------------------------------------------------------|
-| MFD pro 模型   | [Lemon Squeezy](https://ocr.lemonsqueezy.com) | 包含企业版和个人版，可开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn)    | 
-| MFD pro 模型   | [B站工房](https://gf.bilibili.com/item/detail/1102870055)          | 仅包含个人版，不可商用，不能开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) | 
-| MFR pro 模型   | [Lemon Squeezy](https://ocr.lemonsqueezy.com) | 包含企业版和个人版，可开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn)    | 
-| MFR pro 模型   | [B站工房](https://gf.bilibili.com/item/detail/1103052055)          | 仅包含个人版，不可商用，不能开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) | 
-| CnOCR pro 模型 | [Lemon Squeezy](https://ocr.lemonsqueezy.com) | 包含企业版和个人版，可开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) 和 [CnOCR详细资料](https://www.breezedeus.com/article/cnocr) | 
-| CnOCR pro 模型 | [B站工房](https://gf.bilibili.com/item/detail/1104820055) | 仅包含个人版，不可商用，不能开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) 和 [CnOCR详细资料](https://www.breezedeus.com/article/cnocr) | 
+| 模型名称         | 购买地址                                                       | 说明 
+|--------------|------------------------------------------------------------|-----------------------------------------------------------------------------------|
+| MFD pro 模型   | ~~[Lemon Squeezy](https://ocr.lemonsqueezy.com)~~          | 包含企业版和个人版，可开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn)    | 
+| MFD pro 模型   | ~~[B站工房](https://gf.bilibili.com/item/detail/1102870055)~~ | 仅包含个人版，不可商用，不能开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) | 
+| MFR pro 模型   | [Lemon Squeezy](https://ocr.lemonsqueezy.com)              | 包含企业版和个人版，可开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn)    | 
+| MFR pro 模型   | [B站工房](https://gf.bilibili.com/item/detail/1103052055)     | 仅包含个人版，不可商用，不能开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) | 
+| CnOCR pro 模型 | [Lemon Squeezy](https://ocr.lemonsqueezy.com)              | 包含企业版和个人版，可开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) 和 [CnOCR详细资料](https://www.breezedeus.com/article/cnocr) | 
+| CnOCR pro 模型 | [B站工房](https://gf.bilibili.com/item/detail/1104820055)     | 仅包含个人版，不可商用，不能开发票。具体说明见：[P2T详细资料](https://www.breezedeus.com/article/pix2text_cn) 和 [CnOCR详细资料](https://www.breezedeus.com/article/cnocr) | 
 
 购买过程遇到问题可以扫码加小助手为好友进行沟通，备注 `p2t`，小助手会尽快答复：
 
diff --git a/docs/requirements.txt b/docs/requirements.txt
index b65b954..76a0f10 100644
--- a/docs/requirements.txt
+++ b/docs/requirements.txt
@@ -36,7 +36,7 @@ cnocr[ort-cpu]==2.3.0.2
     # via
     #   -r requirements.in
     #   cnocr
-cnstd==1.2.3.6
+cnstd==1.2.4.1
     # via
     #   -r requirements.in
     #   cnocr
diff --git a/docs/usage.md b/docs/usage.md
index c718291..796b686 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -7,7 +7,8 @@ CnOCR 和 CnSTD 中的模型分别存于 `~/.cnocr` 和 `~/.cnstd` 中（Windows
 下载过程请耐心等待，无法科学上网时系统会自动尝试其他可用站点进行下载，所以可能需要等待较长时间。
 对于没有网络连接的机器，可以先把模型下载到其他机器上，然后拷贝到对应目录。
 
-如果系统无法自动成功下载模型文件，则需要手动下载模型文件，可以参考 [huggingface.co/breezedeus](https://huggingface.co/breezedeus) （[国内链接](https://hf-mirror.com/breezedeus)）自己手动下载。
+如果系统无法自动成功下载模型文件，则需要手动下载模型文件，可以参考 [huggingface.co/breezedeus](https://huggingface.co/breezedeus) （[国内镜像](https://hf-mirror.com/breezedeus)）自己手动下载。
+
 具体说明见 [模型下载](models.md)。
 
 
@@ -105,17 +106,16 @@ from pix2text import Pix2Text
 
 text_formula_config = dict(
 	languages=('en', 'ch_sim'),  # 设置识别的语言
-	mfd=dict(  # 声明 LayoutAnalyzer 的初始化参数
-		model_type='yolov7',  # 表示使用的是 YoloV7 模型，而不是 YoloV7_Tiny 模型
-		model_fp=os.path.expanduser(
-			'~/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt'
+	mfd=dict(  # 声明 MFD 的初始化参数
+		model_path=os.path.expanduser(
+			'~/.pix2text/1.1/mfd-onnx/mfd-v20240618.onnx'
 		),  # 注：修改成你的模型文件所存储的路径
 	),
 	formula=dict(
 		model_name='mfr-pro',
 		model_backend='onnx',
 		model_dir=os.path.expanduser(
-			'~/.pix2text/1.0/mfr-pro-onnx'
+			'~/.pix2text/1.1/mfr-pro-onnx'
 		),  # 注：修改成你的模型文件所存储的路径
 	),
 	text=dict(
diff --git a/pix2text/text_formula_ocr.py b/pix2text/text_formula_ocr.py
index ee350a4..66d0b89 100644
--- a/pix2text/text_formula_ocr.py
+++ b/pix2text/text_formula_ocr.py
@@ -12,7 +12,6 @@
 from PIL import Image
 import numpy as np
 import torch
-# from cnstd import LayoutAnalyzer
 from cnstd.utils import box_partial_overlap
 from spellchecker import SpellChecker
 
@@ -130,9 +129,6 @@ def from_config(
         text_ocr = prepare_ocr_engine(languages, text_config)
 
         if enable_formula:
-            # if 'model_name' in mfd_config:
-            #     mfd_config.pop('model_name')
-            # mfd = LayoutAnalyzer(model_name='mfd', **mfd_config)
             mfd = MathFormulaDetector(**mfd_config)
             latex_ocr = LatexOCR(**formula_config)
         else:
@@ -219,8 +215,6 @@ def recognize(
                 * `line_number`: The line number of the box (first line `line_number==0`), boxes with the same value indicate they are on the same line
 
         """
-        # 对于大图片，把图片宽度resize到此大小；宽度比此小的图片，其实不会放大到此大小，
-        # 具体参考：cnstd.yolov7.layout_analyzer.LayoutAnalyzer._preprocess_images 中的 `letterbox` 行
         resized_shape = kwargs.get('resized_shape', 768)
         if isinstance(img, Image.Image):
             img0 = img.convert('RGB')
diff --git a/tests/test_latex_ocr.py b/tests/test_latex_ocr.py
index 60d50a4..fc228d1 100644
--- a/tests/test_latex_ocr.py
+++ b/tests/test_latex_ocr.py
@@ -28,7 +28,7 @@ def test_infer_with_transformers():
     from transformers import TrOCRProcessor
     from optimum.onnxruntime import ORTModelForVision2Seq
 
-    model_dir = os.path.expanduser('~/.pix2text/1.0/mfr-pro-onnx')
+    model_dir = os.path.expanduser('~/.pix2text/1.1/mfr-pro-onnx')
     processor = TrOCRProcessor.from_pretrained(model_dir)
     model = ORTModelForVision2Seq.from_pretrained(model_dir, use_cache=False)
 
diff --git a/tests/test_pix2text.py b/tests/test_pix2text.py
index 3fdce07..7482eff 100644
--- a/tests/test_pix2text.py
+++ b/tests/test_pix2text.py
@@ -12,17 +12,16 @@ def test_recognize_pdf():
     img_fp = f'./docs/examples/{pdf_fn}.pdf'
     text_formula_config = dict(
         languages=('en', 'ch_sim'),
-        mfd=dict(  # 声明 LayoutAnalyzer 的初始化参数
-            model_type='yolov7',  # 表示使用的是 YoloV7 模型，而不是 YoloV7_Tiny 模型
-            model_fp=os.path.expanduser(
-                '~/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt'
+        mfd=dict(  # 声明 MFD 的初始化参数
+            model_path=os.path.expanduser(
+                '~/.pix2text/1.1/mfd-onnx/mfd-v20240618.onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         formula=dict(
             model_name='mfr-pro',
             model_backend='onnx',
             model_dir=os.path.expanduser(
-                '~/.pix2text/1.0/mfr-pro-onnx'
+                '~/.pix2text/1.1/mfr-pro-onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         text=dict(
@@ -96,17 +95,16 @@ def test_blog_example():
     img_fp = './docs/examples/mixed.jpg'
 
     text_formula_config = dict(
-        mfd=dict(  # 声明 LayoutAnalyzer 的初始化参数
-            model_type='yolov7',  # 表示使用的是 YoloV7 模型，而不是 YoloV7_Tiny 模型
-            model_fp=os.path.expanduser(
-                '~/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt'
+        mfd=dict(  # 声明 MFD 的初始化参数
+            model_path=os.path.expanduser(
+                '~/.pix2text/1.1/mfd-onnx/mfd-v20240618.onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         formula=dict(
             model_name='mfr-pro',
             model_backend='onnx',
             model_dir=os.path.expanduser(
-                '~/.pix2text/1.0/mfr-pro-onnx'
+                '~/.pix2text/1.1/mfr-pro-onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
     )
@@ -129,17 +127,16 @@ def test_blog_pro_example():
 
     text_formula_config = dict(
         languages=('en', 'ch_sim'),
-        mfd=dict(  # 声明 LayoutAnalyzer 的初始化参数
-            model_type='yolov7',  # 表示使用的是 YoloV7 模型，而不是 YoloV7_Tiny 模型
-            model_fp=os.path.expanduser(
-                '~/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt'
+        mfd=dict(  # 声明 MFD 的初始化参数
+            model_path=os.path.expanduser(
+                '~/.pix2text/1.1/mfd-onnx/mfd-v20240618.onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         formula=dict(
             model_name='mfr-pro',
             model_backend='onnx',
             model_dir=os.path.expanduser(
-                '~/.pix2text/1.0/mfr-pro-onnx'
+                '~/.pix2text/1.1/mfr-pro-onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         text=dict(
diff --git a/tests/test_text_formula_ocr.py b/tests/test_text_formula_ocr.py
index cb63592..21c12fc 100644
--- a/tests/test_text_formula_ocr.py
+++ b/tests/test_text_formula_ocr.py
@@ -36,17 +36,16 @@ def test_blog_example():
     img_fp = './docs/examples/mixed.jpg'
 
     total_config = dict(
-        mfd=dict(  # 声明 LayoutAnalyzer 的初始化参数
-            model_type='yolov7',  # 表示使用的是 YoloV7 模型，而不是 YoloV7_Tiny 模型
-            model_fp=os.path.expanduser(
-                '~/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt'
+        mfd=dict(  # 声明 MFD 的初始化参数
+            model_path=os.path.expanduser(
+                '~/.pix2text/1.1/mfd-onnx/mfd-v20240618.onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         formula=dict(
             model_name='mfr-pro',
             model_backend='onnx',
             model_dir=os.path.expanduser(
-                '~/.pix2text/1.0/mfr-pro-onnx'
+                '~/.pix2text/1.1/mfr-pro-onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
     )
@@ -65,17 +64,16 @@ def test_blog_pro_example():
 
     total_config = dict(
         languages=('en', 'ch_sim'),
-        mfd=dict(  # 声明 LayoutAnalyzer 的初始化参数
-            model_type='yolov7',  # 表示使用的是 YoloV7 模型，而不是 YoloV7_Tiny 模型
-            model_fp=os.path.expanduser(
-                '~/.cnstd/1.2/analysis/mfd-yolov7-epoch224-20230613.pt'
+        mfd=dict(  # 声明 MFD 的初始化参数
+            model_path=os.path.expanduser(
+                '~/.pix2text/1.1/mfd-onnx/mfd-v20240618.onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         formula=dict(
             model_name='mfr-pro',
             model_backend='onnx',
             model_dir=os.path.expanduser(
-                '~/.pix2text/1.0/mfr-pro-onnx'
+                '~/.pix2text/1.1/mfr-pro-onnx'
             ),  # 注：修改成你的模型文件所存储的路径
         ),
         text=dict(