front end simplify, default vals

app.py

@@ -60,11 +60,11 @@ net, feature_utils, seq_cfg = get_model()
 
 @spaces.GPU(duration=120)
 @torch.inference_mode()
-def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str, seed: int, num_steps: int,
-                   cfg_strength: float, duration: float):
+def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str, seed: 0, num_steps: 25,
+                   cfg_strength: 4.5, duration: 8.0):
 
     rng = torch.Generator(device=device)
-    if seed >= 0:
+    if seed >= 1:
         rng.manual_seed(seed)
     else:
         rng.seed()
@@ -133,8 +133,7 @@ def text_to_audio(prompt: str, negative_prompt: str, seed: int, num_steps: int,
 video_to_audio_tab = gr.Interface(
     fn=video_to_audio,
     description="""
-    Sonisphere
-    Video-to-Audio
+    Sonisphere | Video-to-Audio
     NOTE: It takes longer to process high-resolution videos (>384 px on the shorter side). 
     Doing so does not improve results.
 
@@ -144,14 +143,14 @@ video_to_audio_tab = gr.Interface(
         gr.Video(),
         gr.Text(label='Prompt'),
         gr.Text(label='Negative prompt', value='music'),
-        gr.Number(label='Seed (-1: random)', value=-1, precision=0, minimum=-1),
-        gr.Number(label='Num steps', value=25, precision=0, minimum=1),
-        gr.Number(label='Guidance Strength', value=4.5, minimum=1),
-        gr.Number(label='Duration (sec)', value=8, minimum=1),
+        # gr.Number(label='Seed (-1: random)', value=-1, precision=0, minimum=-1),
+        # gr.Number(label='Num steps', value=25, precision=0, minimum=1),
+        # gr.Number(label='Guidance Strength', value=4.5, minimum=1),
+        # gr.Number(label='Duration (sec)', value=8, minimum=1),
     ],
     outputs='playable_video',
     cache_examples=False,
-    title='MMAudio — Video-to-Audio Synthesis',
+    title='Sonisphere — Video-to-Audio Synthesis',
     examples=[
     ])