diff --git a/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl.md b/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl.md
old mode 100755
new mode 100644
index a1596d938bbcb1656774ea6b2be389edaeae3d5e..f962aaafd634a339911637b285dac8c32477fd7e
--- a/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl.md
+++ b/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl.md
@@ -48,12 +48,19 @@ VisualDL 目前支持以下组件：
 可用于播放输入或生成的音频样本
 
 ### Graph
-兼容 ONNX(Open Neural Network Exchange)[https://github.com/onnx/onnx], 通过与 python SDK的结合，VisualDL可以兼容包括 PaddlePaddle, pytorch, mxnet在内的大部分主流DNN平台。
+
+VisualDL的graph支持paddle program的展示，同时兼容 ONNX(Open Neural Network Exchange)[https://github.com/onnx/onnx]，通过与 python SDK的结合，VisualDL可以兼容包括 PaddlePaddle, pytorch, mxnet在内的大部分主流DNN平台。
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/daming-lu/large_files/master/graph_demo.gif" width="60%" />
+  <img src="https://raw.githubusercontent.com/PaddlePaddle/VisualDL/develop/docs/images/graph_demo.gif" width="60%" />
 </p>
 
+要进行paddle模型的展示，需要进行以下两步操作：
+
+1. 在paddle代码中，调用`fluid.io.save_inference_model()`接口保存模型
+2. 在命令行界面，使用`visualdl --model_pb [paddle_model_dir]` 加载paddle模型
+
+
 ### High Dimensional
 用高维度数据映射在2D/3D来可视化嵌入
 
@@ -235,3 +242,8 @@ board 还支持一下参数来实现远程的访问：
 
 VisualDL 是由 [PaddlePaddle](http://www.paddlepaddle.org/) 和
 [ECharts](http://echarts.baidu.com/) 合作推出的开源项目。我们欢迎所有人使用，提意见以及贡献代码。
+
+## 更多细节
+
+想了解更多关于VisualDL的使用介绍，请查看[文档](https://github.com/PaddlePaddle/VisualDL/tree/develop/demo)
+
diff --git a/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl_en.md b/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl_en.md
old mode 100755
new mode 100644
index 6c86b5ca3a5c7782f203f2b1a31832b24e53281d..67f9f8aae9545e5f46bde73880cedef3830bcd4e
--- a/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl_en.md
+++ b/doc/fluid/user_guides/howto/evaluation_and_debugging/debug/visualdl_en.md
@@ -52,14 +52,21 @@ Image can be used to visualize any tensor or intermediate generated image.
 Audio can be used to play input audio samples or generated audio samples.
 
 ### Graph
-Graph is compatible with ONNX ([Open Neural Network Exchange](https://github.com/onnx/onnx)),
+
+VisualDL graph supports displaying paddle model, furthermore is compatible with ONNX ([Open Neural Network Exchange](https://github.com/onnx/onnx)),
 Cooperated with Python SDK, VisualDL can be compatible with most major DNN frameworks, including
 PaddlePaddle, PyTorch and MXNet.
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/daming-lu/large_files/master/graph_demo.gif" width="60%" />
+  <img src="https://raw.githubusercontent.com/PaddlePaddle/VisualDL/develop/docs/images/graph_demo.gif" width="60%" />
 </p>
 
+To display the paddle model, all you have to do is:
+
+1. call the `fluid.io.save_inference_model()`interface to save paddle model
+2. use `visualdl --model_pb [paddle_model_dir]` to load paddle model in command line
+
+
 ### High Dimensional
 High Dimensional can be used to visualize data embeddings by projecting high-dimensional data into 2D / 3D.
 
@@ -251,3 +258,8 @@ visualDL also supports following optional parameters:
 VisualDL is initially created by [PaddlePaddle](http://www.paddlepaddle.org/) and
 [ECharts](http://echarts.baidu.com/).
 We welcome everyone to use, comment and contribute to Visual DL :)
+
+## More details
+
+For more details about how to use VisualDL, please take a look at [documents](https://github.com/PaddlePaddle/VisualDL/tree/develop/demo)
+