Update the approximated time cost from 500s to 40s. The long time cost may be caused by the unnecessary part of our_ref in inference.

app.py

@@ -97,6 +97,6 @@ demo = gr.Interface(
     examples=examples,
     title='Online demo for `Bilateral Reference for High-Resolution Dichotomous Image Segmentation`',
     description=('Upload a picture, our model will give you the binary maps of the highly accurate segmentation of the salient objects in it. :)'
-                 '\nThe resolution used in our training was `1024x1024`, which is too much burden for the huggingface free spaces like this one (cost ~500s). Please set resolution as more than `768x768` for images with many texture details to obtain good results!\n Ours codes can be found at https://github.com/ZhengPeng7/BiRefNet.')
+                 '\nThe resolution used in our training was `1024x1024`, which is too much burden for the huggingface free spaces like this one (cost nearly 40s). Please set resolution as more than `768x768` for images with many texture details to obtain good results!\n Ours codes can be found at https://github.com/ZhengPeng7/BiRefNet.')
 )
 demo.launch(debug=True)