Update src/app_cached_videos.py

src/app_cached_videos.py

@@ -123,6 +123,7 @@ with gr.Blocks(css=css) as demo:
                 * Click on "Get words" to get the words in the prompt
                 * Select a radio button from the words to visualize the attention mask
                 * Play around with the index of diffusion steps, layers to visualize different masks
+                * Brighter mask corresponds to larger values of attention.
                 """)
 
     with gr.Group("Video Selection"):