Update app.py

app.py

@@ -75,6 +75,6 @@ with gr.Blocks() as demo:
         
     speech_to_text.click(speech_to_text, inputs=audio_file, outputs=text)
     get_image_latent.click(text2image_latent, inputs=[text,steps,width,height,images,diversity], outputs=img)
-    zero_shot_clf.click(zero_shot, inputs=[gallery[0],text_input], outputs = label)
+    zero_shot_clf.click(zero_shot, inputs=[img,text_input], outputs = label)
 
 demo.launch(enable_queue=False)