Update app.py

app.py

@@ -206,17 +206,14 @@ description = f"""
 <div style="text-align: center; font-family: 'Arial', sans-serif;">
     <p>Upload an image and choose a model architecture to see the instance segmentation result generated by the respective model. </p>
     <p>
-        Currently, inference is running on CPU.
-        Performance will be significantly better on GPU.
+        BIG THANKS to Huggingface for funding our demo with their Academic GPU Grant!
     </p>
     <ul>
         <li><strong>SD</strong>: Based on Stable Diffusion 2.
             <a href="https://huggingface.co/{MODEL_IDS['SD']}" target="_blank">Model Link</a>.
-            <em>Approx. CPU inference time: ~1-2 minutes per image.</em>
         </li>
         <li><strong>MAE-H</strong>: Based on Masked Autoencoder (Huge).
             <a href="https://huggingface.co/{MODEL_IDS['MAE-H']}" target="_blank">Model Link</a>.
-            <em>Approx. CPU inference time: ~15-45 seconds per image.</em>
             If you experience tokenizer artifacts or very dark images, you can use gamma correction to handle this. 
         </li>
     </ul>