Update webgui.py

webgui.py

@@ -260,71 +260,76 @@ with gr.Blocks() as demo:
         <a href='https://arxiv.org/abs/2407.08136'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
     </div>
     """)
+    
     with gr.Row():
         with gr.Column(min_width=250):
             uploaded_img = gr.Image(type="filepath", label="Reference Image")
+        with gr.Column(min_width=250):
             uploaded_audio = gr.Audio(type="filepath", label="Input Audio")
+            
+        with gr.Column(min_width=250):
             with gr.Accordion(label=advanced_settings_label, open=False):
-                with gr.Row():
-                    width = gr.Slider(label="Width", minimum=128, maximum=1024, value=default_values["width"], interactive=available_property)
-                    height = gr.Slider(label="Height", minimum=128, maximum=1024, value=default_values["height"], interactive=available_property)
-                with gr.Row():
-                    length = gr.Slider(label="Length", minimum=100, maximum=5000, value=default_values["length"], interactive=available_property)
-                    seed = gr.Slider(label="Seed", minimum=0, maximum=10000, value=default_values["seed"], interactive=available_property)
-                with gr.Row():
-                    facemask_dilation_ratio = gr.Slider(label="Facemask Dilation Ratio", minimum=0.0, maximum=1.0, step=0.01, value=default_values["facemask_dilation_ratio"], interactive=available_property)
-                    facecrop_dilation_ratio = gr.Slider(label="Facecrop Dilation Ratio", minimum=0.0, maximum=1.0, step=0.01, value=default_values["facecrop_dilation_ratio"], interactive=available_property)
-                with gr.Row():
-                    context_frames = gr.Slider(label="Context Frames", minimum=0, maximum=50, step=1, value=default_values["context_frames"], interactive=available_property)
-                    context_overlap = gr.Slider(label="Context Overlap", minimum=0, maximum=10, step=1, value=default_values["context_overlap"], interactive=available_property)
-                with gr.Row():
-                    cfg = gr.Slider(label="CFG", minimum=0.0, maximum=10.0, step=0.1, value=default_values["cfg"], interactive=available_property)
-                    steps = gr.Slider(label="Steps", minimum=1, maximum=100, step=1, value=default_values["steps"], interactive=available_property)
-                with gr.Row():
-                    sample_rate = gr.Slider(label="Sample Rate", minimum=8000, maximum=48000, step=1000, value=default_values["sample_rate"], interactive=available_property)
-                    fps = gr.Slider(label="FPS", minimum=1, maximum=60, step=1, value=default_values["fps"], interactive=available_property)
-                    device = gr.Radio(label="Device", choices=["cuda", "cpu"], value=default_values["device"], interactive=available_property)
+            with gr.Row():
+                width = gr.Slider(label="Width", minimum=128, maximum=1024, value=default_values["width"], interactive=available_property)
+                height = gr.Slider(label="Height", minimum=128, maximum=1024, value=default_values["height"], interactive=available_property)
+            with gr.Row():
+                length = gr.Slider(label="Length", minimum=100, maximum=5000, value=default_values["length"], interactive=available_property)
+                seed = gr.Slider(label="Seed", minimum=0, maximum=10000, value=default_values["seed"], interactive=available_property)
+            with gr.Row():
+                facemask_dilation_ratio = gr.Slider(label="Facemask Dilation Ratio", minimum=0.0, maximum=1.0, step=0.01, value=default_values["facemask_dilation_ratio"], interactive=available_property)
+                facecrop_dilation_ratio = gr.Slider(label="Facecrop Dilation Ratio", minimum=0.0, maximum=1.0, step=0.01, value=default_values["facecrop_dilation_ratio"], interactive=available_property)
+            with gr.Row():
+                context_frames = gr.Slider(label="Context Frames", minimum=0, maximum=50, step=1, value=default_values["context_frames"], interactive=available_property)
+                context_overlap = gr.Slider(label="Context Overlap", minimum=0, maximum=10, step=1, value=default_values["context_overlap"], interactive=available_property)
+            with gr.Row():
+                cfg = gr.Slider(label="CFG", minimum=0.0, maximum=10.0, step=0.1, value=default_values["cfg"], interactive=available_property)
+                steps = gr.Slider(label="Steps", minimum=1, maximum=100, step=1, value=default_values["steps"], interactive=available_property)
+            with gr.Row():
+                sample_rate = gr.Slider(label="Sample Rate", minimum=8000, maximum=48000, step=1000, value=default_values["sample_rate"], interactive=available_property)
+                fps = gr.Slider(label="FPS", minimum=1, maximum=60, step=1, value=default_values["fps"], interactive=available_property)
+                device = gr.Radio(label="Device", choices=["cuda", "cpu"], value=default_values["device"], interactive=available_property)
             generate_button = gr.Button("Generate Video")
-        with gr.Column(min_width=250):
             output_video = gr.Video()
-            gr.Examples(
-                label = "Portrait examples",
-                examples = [
-                    ['assets/test_imgs/a.png'],
-                    ['assets/test_imgs/b.png'],
-                    ['assets/test_imgs/c.png'],
-                    ['assets/test_imgs/d.png'],
-                    ['assets/test_imgs/e.png']
-                ],
-                inputs = [uploaded_img]
-            )
-            gr.Examples(
-                label = "Audio examples",
-                examples = [
-                    ['assets/test_audios/chunnuanhuakai.wav'],
-                    ['assets/test_audios/chunwang.wav'],
-                    ['assets/test_audios/echomimic_en_girl.wav'],
-                    ['assets/test_audios/echomimic_en.wav'],
-                    ['assets/test_audios/echomimic_girl.wav'],
-                    ['assets/test_audios/echomimic.wav'],
-                    ['assets/test_audios/jane.wav'],
-                    ['assets/test_audios/mei.wav'],
-                    ['assets/test_audios/walden.wav'],
-                    ['assets/test_audios/yun.wav'],
-                ],
-                inputs = [uploaded_audio]
-            )
-            gr.HTML("""
-            <div style="display:flex;column-gap:4px;">
-                <a href="https://huggingface.co/spaces/fffiloni/EchoMimic?duplicate=true">
-                    <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-xl.svg" alt="Duplicate this Space">
-                </a>
-                <a href="https://huggingface.co/fffiloni">
-                    <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-me-on-HF-xl-dark.svg" alt="Follow me on HF">
-                </a>
-            </div>
-            """)
-
+    with gr.Row():
+        
+        gr.Examples(
+            label = "Portrait examples",
+            examples = [
+                ['assets/test_imgs/a.png'],
+                ['assets/test_imgs/b.png'],
+                ['assets/test_imgs/c.png'],
+                ['assets/test_imgs/d.png'],
+                ['assets/test_imgs/e.png']
+            ],
+            inputs = [uploaded_img]
+        )
+        gr.Examples(
+            label = "Audio examples",
+            examples = [
+                ['assets/test_audios/chunnuanhuakai.wav'],
+                ['assets/test_audios/chunwang.wav'],
+                ['assets/test_audios/echomimic_en_girl.wav'],
+                ['assets/test_audios/echomimic_en.wav'],
+                ['assets/test_audios/echomimic_girl.wav'],
+                ['assets/test_audios/echomimic.wav'],
+                ['assets/test_audios/jane.wav'],
+                ['assets/test_audios/mei.wav'],
+                ['assets/test_audios/walden.wav'],
+                ['assets/test_audios/yun.wav'],
+            ],
+            inputs = [uploaded_audio]
+        )
+        gr.HTML("""
+        <div style="display:flex;column-gap:4px;">
+            <a href="https://huggingface.co/spaces/fffiloni/EchoMimic?duplicate=true">
+                <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-xl.svg" alt="Duplicate this Space">
+            </a>
+            <a href="https://huggingface.co/fffiloni">
+                <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-me-on-HF-xl-dark.svg" alt="Follow me on HF">
+            </a>
+        </div>
+        """)
+    
     # def generate_video(uploaded_img, uploaded_audio, facemask_dilation_ratio=default_values["facemask_dilation_ratio"],
     #                    facecrop_dilation_ratio=default_values["facecrop_dilation_ratio"],
     #                    context_frames=default_values["context_frames"],