diff --git a/README.md b/README.md
index 66dfd3593d6fc98197d3e1573aa09289b743aef3..4dd0b3d8093bd61033c27522a99f01d674183e68 100644
--- a/README.md
+++ b/README.md
@@ -5,9 +5,8 @@
 Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on [PaddlePaddle](https://github.com/PaddlePaddle/Paddle). 
 
 
-![The Framework of Paddle Graph Learning (PGL)](https://github.com/PaddlePaddle/PGL/blob/master/docs/source/_static/framework_of_pgl.png)
+<img src="https://github.com/PaddlePaddle/PGL/blob/master/docs/source/_static/framework_of_pgl.png" alt="The Framework of Paddle Graph Learning (PGL)" width="1000">
 
-<img src="https://github.com/PaddlePaddle/PGL/blob/master/docs/source/_static/framework_of_pgl.png" alt="The framework of Paddle Graph Learning (PGL)" width="700">
 
 We provide python interfaces for storing/reading/querying graph structured data and two fundamental computational interfaces, which are walk based paradigm and message-passing based paradigm as shown in the above framework of PGL, for building cutting-edge graph learning algorithms.  Combined with the PaddlePaddle deep learning framework, we are able to support both graph representation learning models and graph neural networks, and thus our framework has a wide range of graph-based applications.