update

app.py

@@ -30,6 +30,7 @@ def vggsfm_demo(
     query_frame_num,
     max_query_pts=4096,
 ):
+    torch.cuda.empty_cache()
 
     if input_video is not None:            
         if not isinstance(input_video, str):
@@ -230,6 +231,8 @@ with gr.Blocks() as demo:
         <li>upload the images (.jpg, .png, etc.), or </li> 
         <li>upload a video (.mp4, .mov, etc.) </li> 
     </ul> 
+    <p>The reconstruction should take <strong> up to 1 minute </strong>. </p> 
+    <p>SfM methods are designed for <strong> rigid/static reconstruction </strong>. While it may still work with moving objects, it is best to minimize the presence of such objects in your input data for a good quality. </p> 
     <p>If both images and videos are uploaded, the demo will only reconstruct the uploaded images. By default, we extract one image frame per second from the input video. To prevent crashes on the Hugging Face space, we currently limit reconstruction to the first 20 image frames. </p> 
     <p>If you meet any problem, feel free to create an issue in our <a href="https://github.com/facebookresearch/vggsfm" target="_blank">GitHub Repo</a> ⭐</p> 
     <p>(Please note that running reconstruction on Hugging Face space is slower than on a local machine.) </p> 
@@ -252,7 +255,7 @@ with gr.Blocks() as demo:
     submit_btn = gr.Button("Reconstruct")
 
     examples = [
-        [cake_video, cake_images, 3, 4096],
+        # [cake_video, cake_images, 3, 4096],
         [british_museum_video, british_museum_images, 2, 4096],
     ]