QoL PR

app.py

@@ -112,8 +112,8 @@ with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
         Generate audio from text using a diffusion transformer. Adjust advanced settings for more control.
         """)
 
-        # Basic Input: Text prompt and Audio Length
-        # with gr.Row():
+    # Basic Input: Text prompt
+    with gr.Row():
         text_input = gr.Textbox(
             label="Text Prompt",
             show_label=True,
@@ -121,36 +121,41 @@ with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
             placeholder="Enter your prompt",
             container=True,
             value="a dog barking in the distance",
+            scale=4
         )
-        length_input = gr.Slider(minimum=1, maximum=10, step=1, value=10, label="Audio Length (in seconds)")
-
-        # Output Component
-        result = gr.Audio(label="Result", type="numpy")
-
-        # Advanced settings in an Accordion
-        with gr.Accordion("Advanced Settings", open=False):
-            guidance_scale = gr.Slider(minimum=1.0, maximum=10, step=0.1, value=5.0, label="Guidance Scale")
-            guidance_rescale = gr.Slider(minimum=0.0, maximum=1, step=0.05, value=0.75, label="Guidance Rescale")
-            ddim_steps = gr.Slider(minimum=25, maximum=200, step=5, value=50, label="DDIM Steps")
-            eta = gr.Slider(minimum=0.0, maximum=1.0, step=0.1, value=1.0, label="Eta")
-            seed = gr.Slider(minimum=0, maximum=MAX_SEED, step=1, value=0, label="Seed")
-            randomize_seed = gr.Checkbox(label="Randomize Seed (Disable Seed)", value=True)
-
-        # Examples block
-        gr.Examples(
-            examples=examples,
-            inputs=[text_input]
-        )
-
         # Run button
-        run_button = gr.Button("Generate")
+        run_button = gr.Button("Generate", scale=1)
 
-        # Define the trigger and input-output linking
-        run_button.click(
-            fn=generate_audio,
-            inputs=[text_input, length_input, guidance_scale, guidance_rescale, ddim_steps, eta, seed, randomize_seed],
-            outputs=[result]
-        )
+    # Output Component
+    result = gr.Audio(label="Result", type="numpy")
+
+    # Advanced settings in an Accordion
+    with gr.Accordion("Advanced Settings", open=False):
+        # Audio Length
+        length_input = gr.Slider(minimum=1, maximum=10, step=1, value=10, label="Audio Length (in seconds)")
+        guidance_scale = gr.Slider(minimum=1.0, maximum=10, step=0.1, value=5.0, label="Guidance Scale")
+        guidance_rescale = gr.Slider(minimum=0.0, maximum=1, step=0.05, value=0.75, label="Guidance Rescale")
+        ddim_steps = gr.Slider(minimum=25, maximum=200, step=5, value=50, label="DDIM Steps")
+        eta = gr.Slider(minimum=0.0, maximum=1.0, step=0.1, value=1.0, label="Eta")
+        seed = gr.Slider(minimum=0, maximum=100, step=1, value=0, label="Seed")
+        randomize_seed = gr.Checkbox(label="Randomize Seed (Disable Seed)", value=True)
+
+    # Examples block
+    gr.Examples(
+        examples=examples,
+        inputs=[text_input]
+    )
+
+    # Define the trigger and input-output linking
+    run_button.click(
+        fn=generate_audio,
+        inputs=[text_input, length_input, guidance_scale, guidance_rescale, ddim_steps, eta, seed, randomize_seed],
+        outputs=[result]
+    )
+    text_input.submit(fn=generate_audio,
+        inputs=[text_input, length_input, guidance_scale, guidance_rescale, ddim_steps, eta, seed, randomize_seed],
+        outputs=[result]
+    )
 
 # Launch the Gradio demo
 demo.launch()