From c6791af864372a4d4a2e867415edd7dde55abe60 Mon Sep 17 00:00:00 2001
From: anony-mous-demo <pengzhiliang19@mails.ucas.ac.cn>
Date: Mon, 25 Aug 2025 08:26:44 -0700
Subject: [PATCH] update

---
 README.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 1b78e4c..f0f7f7c 100644
--- a/README.md
+++ b/README.md
@@ -13,9 +13,9 @@ The model can synthesize speech up to **90 minutes** long with up to **4 distinc
 
 Try it out via [Demo](https://microsoft.github.io/VibeVoice).
 
-<p align="center">
-  <img src="Figures/VibeVoice.jpg" alt="VibeVoice Overview" height="240px" style="margin-right: 10px;">
-  <img src="Figures/MOS-preference.png" alt="MOS Preference Results" height="240px">
+<p align="left">
+  <img src="Figures/MOS-preference.png" alt="MOS Preference Results" height="260px">
+  <img src="Figures/VibeVoice.jpg" alt="VibeVoice Overview" height="250px" style="margin-right: 10px;">
 </p>
 
 ## Models