Upload README.md

README.md

@@ -2,21 +2,19 @@
   <img src="imgs/logo.jpg" width="80%" >
 </div>
 
-
 <p align="center">
-    💻 <a href="https://logics.alibaba-inc.com/parsing/?spm=label.2ef5001f.0.0.1c702159dQbTRd">HomePage</a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://github.com/alibaba/Logics-Parsing">GitHub</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://www.modelscope.cn/studios/Alibaba-DT/logix/summary">Demo</a>
+    💻 <a href="https://logics.alibaba-inc.com/parsing/?spm=label.2ef5001f.0.0.1c702159dQbTRd">HomePage</a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://github.com/alibaba/Logics-Parsing">GitHub</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://www.modelscope.cn/studios/Alibaba-DT/Logics-Parsing/summary">Demo</a>
 </p>
 
 
 <div align="center">
-  <img src="imgs/benchmark_clean_morandi_omni.png" alt="OmniDocBench-v1.5 results" style="width: 800px; height: 250px;">
+  <img src="imgs/benchmark_clean_morandi_logicsdocbench.png" alt="LogicsDocBench results" style="width: 800px; height: auto;">
 </div>
-
+<br><br>
 <div align="center">
-  <img src="imgs/benchmark_clean_morandi_logicsdocbench.png" alt="LogicsDocBench results" style="width: 800px; height: 250px;">
+  <img src="imgs/benchmark_clean_morandi_omni.png" alt="OmniDocBench-v1.5 results" style="width: 800px; height: auto;">
 </div>
 
-
 ## Updates
 * [2026/02/13] 🚀🚀🚀🚀🚀 We release Logics-Parsing-v2 Model.
 * [2025/09/25] 🚀🚀🚀We release Logics-Parsing Model.
@@ -26,10 +24,12 @@
 **Logics-Parsing-v2** is an advanced evolution of the previously proposed Logics-Parsing (v1). It inherits all the core capabilities of v1 model, while demonstrating more powerful capabilities on handling complex documents. Furthermore, it extends support for **Parsing-2.0** scenarios, enabling structured parsing of musical sheets, flowcharts, as well as code/pseudocode blocks.
 
 <div align="center">
-  <img src="imgs/overview.png" alt="LogicsDocBench 概览" style="width: 800px; height: 250px;">
+  <img src="imgs/overview.png" alt="LogicsDocBench 概览" style="width: 800px; height: auto;">
 </div>
 
+
 ## Key Features
+
 *   **Effortless End-to-End Processing**
 
     *   End-to-end recognition and parsing for various kinds of document elements within a single model.
@@ -51,6 +51,7 @@
 
 
 ## Benchmark
+
 ### Comparisons on LogicsDocBench
 
 We introduce **LogicsDocBench**, a new comprehensive evaluation benchmark comprising 900 carefully selected PDF pages, covering both traditional document Parsing-1.0 tasks and the newly introduced Parsing-2.0 scenarios. This benchmark is designed to better assess models’ capabilities in complex and diverse real-world documents parsing. The dataset is organized into three core document subsets:
@@ -85,7 +86,7 @@ The histogram below provides a more intuitive visualization of the advantages of
 
 <div align="center">
   <img src="imgs/benchmark_clean_morandi_split.png" width="100%" >
-</div>
+</div><br>
 
 
 ### Comparisons on OmniDocBench_v1.5
@@ -100,6 +101,7 @@ _\* The model results in the table are sourced from the official OmniDocBench we
 
 
 ## Quick Start
+
 ### 1. Installation
 ```shell
 conda create -n logis-parsing-v2 python=3.10
@@ -154,6 +156,7 @@ python3 inference_v2.py --image_path PATH_TO_INPUT_IMG --output_path PATH_TO_OUT
 
 
 
+
 ## Acknowledgments