Update app.py

app.py

@@ -205,3 +205,153 @@ def text_to_audio(
     log.info(f'Saved audio to {audio_save_path}')
 
     return audio_save_path
+
+video_to_audio_tab = gr.Interface(
+    fn=video_to_audio,
+    description="""
+    Project page: <a href="https://hkchengrex.com/MMAudio/">https://hkchengrex.com/MMAudio/</a><br>
+    Code: <a href="https://github.com/hkchengrex/MMAudio">https://github.com/hkchengrex/MMAudio</a><br>
+
+    Ho Kei Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander Schwing, Yuki Mitsufuji
+    
+    University of Illinois Urbana-Champaign, Sony AI, and Sony Group Corporation
+    
+    CVPR 2025
+
+    NOTE: It takes longer to process high-resolution videos (>384 px on the shorter side). 
+    Doing so does not improve results.
+
+    The model has been trained on 8-second videos. Using much longer or shorter videos will degrade performance. Around 5s~12s should be fine.
+    """,
+    inputs=[
+        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),
+    ],
+    outputs='playable_video',
+    cache_examples=False,
+    title='MMAudio — Video-to-Audio Synthesis',
+    examples=[
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_beach.mp4',
+            'waves, seagulls',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_serpent.mp4',
+            '',
+            'music',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_seahorse.mp4',
+            'bubbles',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_india.mp4',
+            'Indian holy music',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_galloping.mp4',
+            'galloping',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_kraken.mp4',
+            'waves, storm',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_nyc.mp4',
+            '',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/mochi_storm.mp4',
+            'storm',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/hunyuan_spring.mp4',
+            '',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/hunyuan_typing.mp4',
+            'typing',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+        [
+            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/hunyuan_wake_up.mp4',
+            '',
+            '',
+            0,
+            25,
+            4.5,
+            10,
+        ],
+    ])
+
+text_to_audio_tab = gr.Interface(
+    fn=text_to_audio,
+    inputs=[
+        gr.Text(label='Prompt'),
+        gr.Text(label='Negative prompt'),
+        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='audio',
+    cache_examples=False,
+    title='MMAudio — Text-to-Audio Synthesis',
+)
+
+if __name__ == "__main__":
+    gr.TabbedInterface([video_to_audio_tab, text_to_audio_tab],
+                       ['Video-to-Audio', 'Text-to-Audio']).launch(allowed_paths=[output_dir])