Update README.md

README.md

@@ -33,6 +33,15 @@ We release the model weights of our best training. The model is trained on the W
 
 As the model CViViT is an autoencoder for videos, here are examples of videos and reconstructions created by the model:
 
+With our logo at Obvious:
+
+![](assets_readme/obvious_example.gif)
+
+
+With the famous blue/red pill from Matrix:
+
+![](assets_readme/matrix_example.gif)
+
 ## * Next steps
 
 We are working on the second part of training of Phenaki, which actually yields the full text-to-video model.