.

app.py

@@ -1,60 +1,79 @@
-import gradio as gr
-import requests
-import base64
 import os
+import uuid
+import base64
+import requests
+import numpy as np
 from PIL import Image
 from io import BytesIO
-import numpy as np
-from gradio_imageslider import ImageSlider  # Assicurati di avere questa libreria installata
-from loadimg import load_img  # Assicurati che questa funzione sia disponibile
-
+from pathlib import Path
 from dotenv import load_dotenv
+import gradio as gr
+from gradio_imageslider import ImageSlider  # Ensure this library is installed
 
-# Carica le variabili di ambiente dal file .env
+# Load environment variables from the .env file
 load_dotenv()
 
-output_folder = 'output_images'
-if not os.path.exists(output_folder):
-    os.makedirs(output_folder)
+# Define the output folder
+output_folder = Path('output_images')
+output_folder.mkdir(exist_ok=True)
 
-def numpy_to_pil(image):
+
+def numpy_to_pil(image: np.ndarray) -> Image.Image:
     """Convert a numpy array to a PIL Image."""
-    if image.dtype == np.uint8:  # Most common case
-        mode = "RGB"
-    else:
-        mode = "F"  # Floating point
+    mode = "RGB" if image.dtype == np.uint8 else "F"
     return Image.fromarray(image.astype('uint8'), mode)
 
 
-def process_image(image):
-    image = numpy_to_pil(image)  # Convert numpy array to PIL Image
+def process_image(image: np.ndarray):
+    """
+    Process the input image by sending it to the backend and saving the output.
+
+    Args:
+        image (np.ndarray): Input image in numpy array format.
+
+    Returns:
+        tuple: Processed images and the path to the saved image.
+    """
+    # Convert numpy array to PIL Image
+    image_pil = numpy_to_pil(image)
+
+    # Encode image to base64
     buffered = BytesIO()
-    image.save(buffered, format="PNG")
+    image_pil.save(buffered, format="PNG")
     img_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
+
+    # Send image to backend
     response = requests.post(
         os.getenv('BACKEND_URL'),
         files={"file": ("image.png", base64.b64decode(img_str), "image/png")}
     )
+
+    # Process the response
     result = response.json()
     processed_image_b64 = result["processed_image"]
     processed_image = Image.open(BytesIO(base64.b64decode(processed_image_b64)))
-    #return [image, processed_image]  # Return the original and processed image
-    image_path = os.path.join(output_folder, "no_bg_image.png")
+
+    # Save the processed image
+    image_path = output_folder / f"no_bg_image_{uuid.uuid4().hex}.png"
     processed_image.save(image_path)
-    return (processed_image, image), image_path
 
+    return (processed_image, image_pil), str(image_path)
 
-# Carica l'esempio di immagine
-chameleon = load_img("elephant.jpg", output_type="pil")
 
+# Define inputs and outputs for the Gradio interface
 image = gr.Image(label="Upload a photo")
 output_slider = ImageSlider(label="Processed photo", type="pil")
+
 demo = gr.Interface(
     fn=process_image,
     inputs=image,
     outputs=[output_slider, gr.File(label="output png file")],
     title="Magic Eraser",
-    examples=[["elephant.jpg"]]  # Esempio locale
+    examples=[
+        ["images/elephant.jpg"],
+        ["images/lion.png"],
+        ["images/tartaruga.png"],
+    ]
 )
 
 if __name__ == "__main__":