diff --git a/doc/DESIGN_DOC.md b/doc/DESIGN_DOC.md
index 2b051ec9aea10cf8d3e4c287bed753657b00c480..b8169b43b63c9f2548a29d454eb24f8577b755ef 100644
--- a/doc/DESIGN_DOC.md
+++ b/doc/DESIGN_DOC.md
@@ -172,10 +172,11 @@ After sufficient offline evaluation of the model, online A/B test is usually nee
 
 <p align="center">
     <br>
-<img src='abtest.png' style="zoom:33%;">
+<img src='abtest.png' width = "345" height = "230">
     <br>
 <p>
 
+
 ### 3.3 Model Online Reloading     
 
 In order to ensure the availability of services, the model needs to be hot loaded without service interruption. Paddle Serving supports this feature and provides a tool for monitoring output models to update local models. Please refer to [Hot loading in Paddle Serving](HOT_LOADING_IN_SERVING.md) for specific examples.
diff --git a/doc/DESIGN_DOC_CN.md b/doc/DESIGN_DOC_CN.md
index 9a045ffb00aceddbe7af846897cf7f4d18ebee26..c068ac35bb6beebe70a6f873318c6d5059fc51e7 100644
--- a/doc/DESIGN_DOC_CN.md
+++ b/doc/DESIGN_DOC_CN.md
@@ -168,10 +168,11 @@ Paddle Serving的核心执行引擎是一个有向无环图，图中的每个节
 
 <p align="center">
     <br>
-<img src='abtest.png' style="zoom:33%;">
+<img src='abtest.png' width = "345" height = "230">
     <br>
 <p>
 
+
 ### 3.3 模型热加载
 
 为了保证服务的可用性，需要在服务不中断的情况下对模型进行热加载。Paddle Serving对该特性进行了支持，并提供了一个监控产出模型更新本地模型的工具，具体例子请参考[Paddle Serving中的模型热加载](HOT_LOADING_IN_SERVING_CN.md)。