Update app.py

app.py

@@ -67,6 +67,7 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from PIL import Image
 import io
+import base64
 
 client = InferenceClient("meta-llama/Llama-3.2-11B-Vision-Instruct")
 
@@ -91,14 +92,15 @@ def respond(
     # Add the current user message
     messages.append({"role": "user", "content": message})
 
-    # Convert the PIL image to a byte stream
+    # Convert the image to a base64-encoded string
     image_bytes = io.BytesIO()
     image.save(image_bytes, format='PNG')
     image_bytes.seek(0)
+    image_base64 = base64.b64encode(image_bytes.getvalue()).decode('utf-8')
 
     # Use InferenceClient to handle the image and text input to the model
-    # Pass the text message as the 'prompt'
-    response_data = client.text_to_image(images=image_bytes, prompt=message)  # Add 'prompt' as required
+    # Pass the base64-encoded image as the input
+    response_data = client.text_to_image(images=image_base64, prompt=message)  # Pass the base64 string as 'images'
 
     # Process the response from the model
     response = ""
@@ -122,4 +124,3 @@ demo = gr.ChatInterface(
 
 if __name__ == "__main__":
     demo.launch(share=True)  # Set share=True to create a public link
-