Update app.py

app.py

@@ -5,9 +5,16 @@ from IPython.display import Audio as IPythonAudio
 itt_pipe = pipeline("image-to-text",
                 model="Salesforce/blip-image-captioning-base")
 
-
+def get_pipeline_prediction(pil_image):
+    
+    pipeline_output = itt_pipe(pil_image)
+    
+    processed_image = render_results_in_image(pil_image,
+                                            pipeline_output)
+    return processed_image
+    
 text = gr.Interface(
-    fn=itt_pipe,
+    fn=get_pipeline_prediction,
     inputs=gr.Image(label="Input image", type="pil"), outputs=gr.Image(label="Text describe the image", type="pil")
 )
 text.launch()