Reduce the description

README.md

@@ -53,14 +53,8 @@ widget:
   <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
     <h2 style="color: #24292e; margin-top: 0;">Overview</h2>
     <p>This repository contains a lightweight temporal adapter for Kandinsky-5 image-to-video generation.</p>
-    <p>The adapter is intended for motion tempo control with two temporal signals: global FPS conditioning and latent-time conditioning.</p>
     <p>Lower target FPS typically leads to slower perceived motion, while higher target FPS leads to faster perceived motion.</p>
   </div>
-  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
-    <h2 style="color: #24292e; margin-top: 0;">Behavior</h2>
-    <p>The adapter is designed to work on top of a base I2V model and inject temporal control without requiring full end-to-end finetuning of the generator.</p>
-    <p>In practice, the final video quality, visual consistency, and motion realism still depend strongly on the underlying base image-to-video model.</p>
-  </div>
   <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
     <h2 style="color: #24292e; margin-top: 0;">Examples</h2>
     <p>The gallery below shows FTTA examples for pose motion control and forest motion control at different target FPS values.</p>