Update app.py

app.py

@@ -14,14 +14,30 @@ controlnet = ControlNetModel.from_pretrained("lauraibnz/midi-audioldm", torch_dt
 pipe = AudioLDMControlNetPipeline.from_pretrained("cvssp/audioldm-m-full", controlnet=controlnet, torch_dtype=torch_dtype)
 pipe = pipe.to(device)
 
-def predict(midi_file=None, prompt="", audio_length_in_s=5, controlnet_conditioning_scale=1, num_inference_steps=20):
+def predict(midi_file=None, prompt="", negative_prompt="", audio_length_in_s=5, controlnet_conditioning_scale=1, num_inference_steps=20, guess_mode=False):
     if midi_file:
         midi_file = midi_file.name
     else:
         midi_file = "test.mid"
     midi = PrettyMIDI(midi_file)
-    audio = pipe(prompt, midi=midi, audio_length_in_s=audio_length_in_s, num_inference_steps=num_inference_steps, controlnet_conditioning_scale=float(controlnet_conditioning_scale))
+    audio = pipe(
+        prompt,
+        negative_prompt=negative_prompt,
+        midi=midi, 
+        audio_length_in_s=audio_length_in_s, 
+        num_inference_steps=num_inference_steps, 
+        controlnet_conditioning_scale=float(controlnet_conditioning_scale),
+        guess_mode=guess_mode
+    )
     return (16000, audio.audios.T)
 
-demo = gr.Interface(fn=predict, inputs=[gr.File(file_types=[".mid"]), "text", gr.Slider(0, 30, value=5, step=5, label="duration (seconds)"), gr.Slider(0.0, 1.0, value=1.0, step=0.1, label="conditioning scale")], outputs="audio")
+demo = gr.Interface(fn=predict, inputs=[
+    gr.File(file_types=[".mid"]), 
+    "text",
+    gr.Textbox(label="negative prompt")
+    gr.Slider(0, 30, value=5, step=5, label="duration (seconds)"), 
+    gr.Slider(0.0, 1.0, value=1.0, step=0.1, label="conditioning scale"),
+    gr.Slider(0, 50, value=20, step=0.1, label="inference steps"),
+    gr.Checkbox(label="guess mode")
+], outputs="audio")
 demo.launch()