Update app.py

app.py

@@ -6,7 +6,15 @@ itt_pipe = pipeline("image-to-text",
                 model="Salesforce/blip-image-captioning-base")
 
 
-text = itt_pipe(input)
+text = gr.Interface(
+  fn=itt_pipe,
+  inputs=gr.Image(label="Input image", 
+                  type="pil"),
+  outputs=gr.Image(label="Text describe the image",
+                   type="pil")
+)
+
+#text = itt_pipe(input)
 
 
 tts_pipe = pipeline("text-to-speech",