Update app.py

app.py

@@ -145,7 +145,6 @@ def age_filter(image, input_age, output_age):
     input_image = transform_resize(image=np.array(image))['image']/255
 
 
-    #input_image=(dataset[0]['normalized_input_image'])
     age_map1 = torch.full((1, 512, 512), input_age / 100)
     age_map2 = torch.full((1, 512, 512),  output_age / 100)
 
@@ -175,26 +174,19 @@ def crop_and_process_image(input_img,input_age,output_ag):
     # Return the output
     return output
 
-# Define the input image component with the crop tool
+input_image = gr.Image(label="Input Image", interactive=True)
 
-# Define the output image component
 output_image = gr.Image(label="Output Image", type="pil")
 
-
 input_age = gr.Slider(label="Current Age")
 output_age = gr.Slider(label="Desired Age")
 
 
-# Define the function to be called when the button is pressed
 def process_image(input_img,input_age,output_age):
-    # Convert the input image to a PyTorch tensor
 
-    # Call the crop_and_process_image function
     output = crop_and_process_image(input_img,input_age,output_age)
 
-    # Convert the output tensor to a NumPy array and return it
     output = Image.fromarray(output)
-    output.show()
     return output
     
 description="Enter age of input image and desired age. Crop out face. Better results on high resolution." 
@@ -202,4 +194,4 @@ description="Enter age of input image and desired age. Crop out face. Better res
 
 
 # Create the Gradio interface
-gr.Interface(fn=process_image, inputs=[gr.Image(source="upload", type="filepath", label="init_img | 512*512 px"),input_age,output_age], outputs=output_image,description=description, title="Age Transformation").launch(debug=True)
+gr.Interface(fn=process_image, inputs=[input_image,input_age,output_age], outputs=output_image,description=description, title="Age Transformation").launch(debug=True)