change 'please note'

app.py

@@ -405,7 +405,7 @@ if __name__ == "__main__":
             <li><strong>Visualize:</strong> The 3D reconstruction will appear in the viewer on the right. You can rotate, pan, and zoom to explore the model, and download the GLB file.</li>
             <li><strong>Downstream:</strong> The 3D output can be used as reconstruction or for monocular camera calibration.</li>
         </ol>
-        <p><strong style="color: #ff7e26;">Please note:</strong> <span style="color: #ff7e26; font-weight: bold;">Our model runs on CPU on HuggingFace Space. Actual inference is less than 100ms second per image on consumer-level GPUs. However, while running on HuggingFace Space's CPU without acceleration you can go grab a coffee, it will take between 10 seconds and 3 minutes, depending on the "Utilized Model" and "Speed-Resolution Tradeoff" chosen. Web-based 3D pointcloud visualization may be slow due to Gradio's rendering. For faster visualization, use a local machine to run our demo from our <a href="https://github.com/lpiccinelli-eth/UniK3D">GitHub repository</a>. </span></p>
+        <p><strong style="color: #ff7e26;">PLEASE NOTE:</strong> <span style="color: #ff7e26; font-weight: bold;">UniK3D currently runs on CPU here on HuggingFace. Actual inference is less than 100ms second per image on consumer-level GPUs. However, while running on HuggingFace Space's CPU, it will take between 10 seconds and 3 minutes, depending on the "Utilized Model" and "Speed-Resolution Tradeoff" chosen, please wait. For faster visualization, use a local machine to run our demo from our <a href="https://github.com/lpiccinelli-eth/UniK3D">GitHub repository</a>. </span></p>
         </div>
         """
         )