update

app.py

@@ -12,12 +12,12 @@ with gr.Blocks() as demo:
                 <p align="center"><a href="https://github.com/Zeqiang-Lai/Anything2Image"><b>https://github.com/Zeqiang-Lai/Anything2Image</b></p>
                 """)
         gr.Interface(fn=anything2img, 
-                     inputs=[gr.Textbox(placeholder="Enter a prompt in addition to the audio, image, text condition below", label="Prompt (Optional)"),
-                             gr.Audio(label="Audio Condition"), 
-                             gr.Image(label="Image Condition"), 
-                             gr.Textbox(label="Text Condition"),
+                     inputs=["text",
+                             "audio", 
+                             "image", 
+                             "text",
                              ], 
-                     outputs=[gr.Image(label="Generated Image")],
+                     outputs="text",
                      examples=[['', 'assets/wav/dog_audio.wav', None, None],
                                ['A painting', 'assets/wav/cat.wav', None, None],
                                ['', 'assets/wav/wave.wav', 'assets/image/bird.png', None],