diff --git a/README.md b/README.md
index d3eab4e..b9b0df4 100644
--- a/README.md
+++ b/README.md
@@ -67,10 +67,10 @@ MuseTalk was trained in latent spaces, where the images were encoded by a freeze
-
+
|
-
+
|
@@ -140,6 +140,21 @@ MuseTalk was trained in latent spaces, where the images were encoded by a freeze
* For video dubbing, we applied a self-developed tool which can detect the talking person.
+## Some interesting videos!
+
+
+ | Image |
+ MuseV + MuseTalk |
+
+
+
+ 
+ |
+
+
+ |
+
+
# TODO:
- [x] trained models and inference codes.