From efcce2c338bbda9def93fbaa583fe6db0605671b Mon Sep 17 00:00:00 2001
From: Mingxue-Xu <92848346+Mingxue-Xu@users.noreply.github.com>
Date: Mon, 6 Dec 2021 14:28:48 +0800
Subject: [PATCH] Update README.md

Add more explanation of the demos readme.
---
 demos/metaverse/README.md | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/demos/metaverse/README.md b/demos/metaverse/README.md
index 4238c450..cf649522 100644
--- a/demos/metaverse/README.md
+++ b/demos/metaverse/README.md
@@ -1,7 +1,23 @@
 # Metaverse
+
+## Introduction
+This demo is an implementation to let a celebrity in an image "speak". With the composition of PaddleSpeech and PaddleGAN, we integrate the installation and the specific modules in a single shell script. 
+
+## How to use our code
+
 You can make your favorite person say the specified content with the `TTS` mudule of `PaddleSpeech` and `PaddleGAN`, and construct your own virtual human.
 
-Run the following command line to get started:
+First, locate the directory you would like to run our code, and set the environment variants. 
+```shell
+./path.sh
 ```
+Download the celebrity image in the current directory, in our case we use `Lamarr.png`.
+
+Second, run `run.sh` to complete all the essential procedures, including the installation.  
+
+```shell
 ./run.sh
 ```
+If you would like to try your own image, please replace the image name in the shell script.
+
+The result has shown on our notebook[]().