added extra params

app.py

@@ -19,7 +19,7 @@ def load_model():
 
 # Function to set up, generate, and process the audio
 @spaces.GPU(duration=120)  # Allocate GPU only when this function is called
-def generate_audio(prompt, seconds_total=30, steps=100, cfg_scale=7):
+def generate_audio(prompt, sampler_type_dropdown, seconds_total=30, steps=100, cfg_scale=7,sigma_min_slider=0.3,sigma_max_slider=500):
     print(f"Prompt received: {prompt}")
     print(f"Settings: Duration={seconds_total}s, Steps={steps}, CFG Scale={cfg_scale}")
 
@@ -56,9 +56,9 @@ def generate_audio(prompt, seconds_total=30, steps=100, cfg_scale=7):
         cfg_scale=cfg_scale,
         conditioning=conditioning,
         sample_size=sample_size,
-        sigma_min=0.3,
-        sigma_max=500,
-        sampler_type="dpmpp-3m-sde",
+        sigma_min=sigma_min_slider,
+        sigma_max=sigma_max_slider,
+        sampler_type=sampler_type_dropdown,#"dpmpp-3m-sde",
         device=device
     )
     print("Audio generated.")
@@ -85,11 +85,16 @@ def generate_audio(prompt, seconds_total=30, steps=100, cfg_scale=7):
 # Setting up the Gradio Interface
 interface = gr.Interface(
     fn=generate_audio,
+    
     inputs=[
         gr.Textbox(label="Prompt", placeholder="Enter your text prompt here"),
+        gr.Dropdown(["dpmpp-2m-sde", "dpmpp-3m-sde", "k-heun", "k-lms", "k-dpmpp-2s-ancestral", "k-dpm-2", "k-dpm-fast"], label="Sampler type", value="dpmpp-3m-sde"),
         gr.Slider(0, 47, value=30, label="Duration in Seconds"),
         gr.Slider(10, 150, value=100, step=10, label="Number of Diffusion Steps"),
-        gr.Slider(1, 15, value=7, step=0.1, label="CFG Scale")
+        gr.Slider(1, 15, value=7, step=0.1, label="CFG Scale"),        
+        gr.Slider(minimum=0.0, maximum=5.0, step=0.01, value=0.3, label="Sigma min"),
+        gr.Slider(minimum=0.0, maximum=1000.0, step=0.1, value=500, label="Sigma max"),
+
     ],
     outputs=gr.Audio(type="filepath", label="Generated Audio"),
     title="Stable Audio Generator",