Update app.py

app.py

@@ -101,11 +101,11 @@ with gr.Blocks(css=css) as demo:
                 Note: Only the first 30 seconds of your audio will be used for inference.
                 </p>
             </div>""")
-        audio_input = gr.Audio(type="filepath", source="upload")
+        audio_input = gr.Audio(label="Music input", type="filepath", source="upload")
         infer_btn = gr.Button("Generate Image from Music")
         #lpmc_cap = gr.Textbox(label="Lp Music Caps caption")
         #llama_trans_cap = gr.Textbox(label="Llama translation")
-        img_result = gr.Gallery(label="Result", grid=2)
+        img_result = gr.Image(label="Image Result")
 
     #infer_btn.click(fn=infer, inputs=[audio_input], outputs=[lpmc_cap, llama_trans_cap, img_result])
     infer_btn.click(fn=infer, inputs=[audio_input], outputs=[img_result])