update lightweight code

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pretrained_models/sam_vit_b_01ec64.pth filter=lfs diff=lfs merge=lfs -text

app.py

@@ -132,8 +132,8 @@ interface = gr.Interface(
     Image.txt. This code support image to text transformation. Then the generated text can do retrieval, question answering et al to conduct zero-shot.
     \n Github: https://github.com/showlab/Image2Paragraph
     \n Twitter: https://twitter.com/awinyimgprocess/status/1646225454599372800?s=46&t=HvOe9T2n35iFuCHP5aIHpQ
-    \n Since GPU is expensive, we use CPU for demo and not include semantic segment anything. Run code local with gpu or google colab we provided for fast speed.
-    \n Ttext2image model is controlnet ( very slow in cpu(~2m)), which used canny edge as reference.
+    \n For online demo, we use smallest model to speed up. For better result, look for github for details.
+    \n Ttext2image model is controlnet, which used canny edge as reference.
     \n To speed up, we generate image with small size 384, run the code local for high-quality sample.
     """
 )