rng seed

app.py

@@ -60,14 +60,15 @@ 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: 0, num_steps: 25,
+def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str, num_steps: 25,
                    cfg_strength: 4.5, duration: 8.0):
 
     rng = torch.Generator(device=device)
-    if seed >= 0:
-        rng.manual_seed(seed)
-    else:
-        rng.seed()
+    # if seed >= 0:
+    #     rng.manual_seed(seed)
+    # else:
+    rng.seed()
+
     fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=num_steps)
 
     video_info = load_video(video, duration)
@@ -102,6 +103,7 @@ video_to_audio_tab = gr.Interface(
     fn=video_to_audio,
     description="""
     Video-to-Audio
+
     NOTE: It takes longer to process high-resolution videos (>384 px on the shorter side). 
     Doing so does not improve results.
 
@@ -118,7 +120,7 @@ video_to_audio_tab = gr.Interface(
     ],
     outputs='playable_video',
     cache_examples=False,
-    title='Sonisphere — Sonic Branding Synthesis',
+    title='Sonisphere — Sonic Branding with Multi-modal Audio Synthesis',
     examples=[
     ])