Update app.py

app.py

@@ -22,6 +22,8 @@ def inference(image, size):
     if image is None:
         raise gr.Error("Image not uploaded")
         
+    # Store original image for comparison
+    original_image = image.copy()
 
     if torch.cuda.is_available():
         torch.cuda.empty_cache()
@@ -55,22 +57,36 @@ def inference(image, size):
             result = model2.predict(image.convert('RGB'))
             
     print(f"Image size ({device}): {size} ... OK")
-    return result
+    # Return tuple of original and processed images for the slider
+    return (original_image, result)
 
 
-title = "ProFaker"
+title = """<h1 align="center">ProFaker</h1>"""
 
+with gr.Blocks() as demo:
+    gr.HTML(title)
+    
+    with gr.Row():
+        with gr.Column():
+            input_image = gr.Image(type="pil", label="Input Image")
+            size_select = gr.Radio(
+                ["2x", "4x", "8x"],
+                type="value",
+                value="2x",
+                label="Resolution model"
+            )
+            process_btn = gr.Button("Upscale Image")
+            
+        with gr.Column():
+            result_slider = ImageSlider(
+                interactive=False,
+                label="Before and After Comparison"
+            )
+    
+    process_btn.click(
+        fn=inference,
+        inputs=[input_image, size_select],
+        outputs=result_slider
+    )
 
-gr.Interface(inference,
-    [gr.Image(type="pil"), 
-    gr.Radio(["2x", "4x", "8x"], 
-    type="value",
-    value="2x",
-    label="Resolution model")], 
-    ImageSlider(interactive = False, type="pil", label="Output"),
-    title=title,
-    flagging_mode="never",
-    cache_mode="lazy",
-    delete_cache=(44000, 44000),
-    ).queue(api_open=True).launch(show_error=True, show_api=True)
-    
+demo.queue(api_open=True).launch(show_error=True, show_api=True)