fast process

app.py

@@ -72,6 +72,8 @@ def process_image(image_src, options=None, processor=None):
             <h3>Region Semantic</h3>
             <p>{region_semantic}</p>
         </div>
+    </div>
+    <div style="display: flex; flex-wrap: wrap;">
         <div style="flex: 1;">
             <h3>GPT4 Reasoning:</h3>
             <p>{gen_text}</p>
@@ -123,7 +125,7 @@ interface = gr.Interface(
     \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 To speed up, we generate image with small size 256, run the code local for high-quality sample.
+    \n To speed up, we generate image with small size 384, run the code local for high-quality sample.
     """
 )
 

utils/util.py

@@ -15,7 +15,7 @@ def read_image_width_height(image_path):
     return width, height
 
 
-def resize_long_edge(image, target_size=256):
+def resize_long_edge(image, target_size=384):
     # Calculate the aspect ratio
     width, height = image.size
     aspect_ratio = float(width) / float(height)