diff --git a/README.md b/README.md
index 4eb861c491ec72582184dc5d54163a94a066590f..b7fb931e25efacb70456cf631171aefe0dfc1f92 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,10 @@
 [中文](https://github.com/PaddlePaddle/Serving/blob/develop/README_CN.md)
 
 ## Motivation
-Paddle Serving helps deep learning developers deploy an online inference service without much effort. **The goal of this project**: once you have trained a deep neural nets with [Paddle](https://github.com/PaddlePaddle/Paddle), you already have a model inference service. 
+Paddle Serving helps deep learning developers deploy an online inference service without much effort. **The goal of this project**: once you have trained a deep neural nets with [Paddle](https://github.com/PaddlePaddle/Paddle), you already have a model inference service. An demo of serving is as follows:
+<p align="center">
+    <img src="/demo.gif?raw=true" width="700">
+</p>
 
 ## Key Features
 - Integrate with Paddle training pipeline seemlessly, most paddle models can be deployed **with one line command**.