Update app.py

app.py

@@ -1,8 +1,30 @@
+import base64
+
 import gradio as gr
+import io
+
 from PIL import Image
+
 import spaces
+
 from transformers import pipeline
 
+def image_to_base64_str(pil_image: Image.Image) -> str:
+    """
+    Converts a PIL image to a base64 encoded string.
+
+    Args:
+        pil_image (Image.Image): The PIL image to be converted.
+
+    Returns:
+        str: The base64 encoded string representation of the image.
+    """
+    byte_arr = io.BytesIO()
+    pil_image.save(byte_arr, format='PNG')
+    byte_arr = byte_arr.getvalue()
+    return str(base64.b64encode(byte_arr).decode('utf-8'))
+
+
 # Initialize Model
 get_completion = pipeline("image-to-text",model="Salesforce/blip-image-captioning-base", device=0)
 
@@ -17,7 +39,9 @@ def captioner(input: Image.Image) -> str:
     Returns:
         str: The generated caption text.
     """
-    output = get_completion(input)
+    
+    base64_image = image_to_base64_str(image)
+    output = get_completion(base64_image)
     return output[0]['generated_text']
 
 ####### GRADIO APP #######
@@ -42,6 +66,7 @@ with demo:
   interface = gr.Interface(fn=captioner,
                     inputs=[gr.Image(label="Upload image", type="pil")],
                     outputs=[gr.Textbox(label="Caption")],
-                    allow_flagging="never")
+                    allow_flagging="never",
+                    examples=["christmas_dog.jpeg", "bird_flight.jpeg", "cow.jpeg"]))
 
 demo.launch()