update

app.py

@@ -27,6 +27,7 @@ def driver(uploaded_image):
   
 def clip_intero_inference(uploaded_image):
   prompt = img_to_text(uploaded_image, fn_index=1)[0]
+  print(f"CLip interrogator prompt is : {prompt}")
   return prompt
 
 def voicetojoke_inference(prompt):
@@ -68,10 +69,11 @@ with gr.Blocks() as demo:
 
   with gr.Row():
     #sample
-    out_prompt = gr.Textbox() #HTML(label="First News Link", show_label=True) 
+    out_image = gr.Image()
+    #out_prompt = gr.Textbox() #HTML(label="First News Link", show_label=True) 
     #out_dataframe = gr.Dataframe(wrap=True, datatype = ["str", "str", "markdown", "markdown", "str"])
     
-  b1.click(fn=clip_intero_inference, inputs=in_image, outputs=out_prompt)
+  b1.click(fn=driver, inputs=in_image, outputs=out_image)
   #b2.click(fn=inference, inputs=in_newssource, outputs=out_dataframe)
 
 demo.launch(debug=True, show_error=True)