Update app.py

app.py

@@ -1,57 +1,55 @@
-import os, sys
+import os
+import sys
 import tempfile
 import gradio as gr
-from src.gradio_demo import SadTalker  
+from src.gradio_demo import SadTalker
 # from src.utils.text2speech import TTSTalker
 from huggingface_hub import snapshot_download
 
-def get_source_image(image):   
-        return image
+def get_source_image(image):
+    return image
 
+in_webui = False
 try:
     import webui  # in webui
     in_webui = True
 except:
-    in_webui = False
-
+    pass
 
 def toggle_audio_file(choice):
     if choice == False:
         return gr.update(visible=True), gr.update(visible=False)
     else:
         return gr.update(visible=False), gr.update(visible=True)
-    
+
 def ref_video_fn(path_of_ref_video):
     if path_of_ref_video is not None:
         return gr.update(value=True)
     else:
         return gr.update(value=False)
-    
+
 def download_model():
     REPO_ID = 'vinthony/SadTalker-V002rc'
     snapshot_download(repo_id=REPO_ID, local_dir='./checkpoints', local_dir_use_symlinks=True)
 
 def sadtalker_demo():
-
     download_model()
-
     sad_talker = SadTalker(lazy_load=True)
     # tts_talker = TTSTalker()
 
     with gr.Blocks(analytics_enabled=False) as sadtalker_interface:
         gr.Markdown("<div align='center'> <h2> SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation (CVPR 2023) </span> </h2> ")
-        
-        
+
         gr.Markdown("""
         <b>Business အတွက် သီးသန့် အသုံးပြုလိုပါက သီးသန့် Plan ဝယ်ယူပြီး အသုံးပြုနိုင်ပါတယ်)
-        
-        with gr.Row(): #.style(equal_height=False):
+        """)
+
+        with gr.Row():
             with gr.Column(variant='panel'):
                 with gr.Tabs(elem_id="sadtalker_source_image"):
                     with gr.TabItem('Source image'):
                         with gr.Row():
-                            source_image = gr.Image(label="Source image", source="upload", type="filepath", elem_id="img2img_image") # .style(width=512)
-
+                            source_image = gr.Image(label="Source image", source="upload", type="filepath", elem_id="img2img_image")
 
                 with gr.Tabs(elem_id="sadtalker_driven_audio"):
                     with gr.TabItem('Driving Methods'):
@@ -64,70 +62,65 @@ def sadtalker_demo():
                             with gr.Column():
                                 use_idle_mode = gr.Checkbox(label="Use Idle Animation")
                                 length_of_audio = gr.Number(value=5, label="The length(seconds) of the generated video.")
-                                use_idle_mode.change(toggle_audio_file, inputs=use_idle_mode, outputs=[driven_audio, driven_audio_no]) # todo
+                                use_idle_mode.change(toggle_audio_file, inputs=use_idle_mode, outputs=[driven_audio, driven_audio_no])
 
                         with gr.Row():
-                            ref_video = gr.Video(label="Reference Video", source="upload", type="filepath", elem_id="vidref") # .style(width=512)
+                            ref_video = gr.Video(label="Reference Video", source="upload", type="filepath", elem_id="vidref")
 
                             with gr.Column():
                                 use_ref_video = gr.Checkbox(label="Use Reference Video")
                                 ref_info = gr.Radio(['pose', 'blink','pose+blink', 'all'], value='pose', label='Reference Video',info="How to borrow from reference Video?((fully transfer, aka, video driving mode))")
 
-                            ref_video.change(ref_video_fn, inputs=ref_video, outputs=[use_ref_video]) # todo
-
+                            ref_video.change(ref_video_fn, inputs=ref_video, outputs=[use_ref_video])
 
-            with gr.Column(variant='panel'): 
+            with gr.Column(variant='panel'):
                 with gr.Tabs(elem_id="sadtalker_checkbox"):
                     with gr.TabItem('Settings'):
-                        gr.Markdown("need help? please visit our [[best practice page](https://github.com/OpenTalker/SadTalker/blob/main/docs/best_practice.md)] for more detials")
+                        gr.Markdown("need help? please visit our [[best practice page](https://github.com/OpenTalker/SadTalker/blob/main/docs/best_practice.md)] for more details")
                         with gr.Column(variant='panel'):
-                            # width = gr.Slider(minimum=64, elem_id="img2img_width", maximum=2048, step=8, label="Manually Crop Width", value=512) # img2img_width
-                            # height = gr.Slider(minimum=64, elem_id="img2img_height", maximum=2048, step=8, label="Manually Crop Height", value=512) # img2img_width
                             with gr.Row():
-                                pose_style = gr.Slider(minimum=0, maximum=45, step=1, label="Pose style", value=0) #
-                                exp_weight = gr.Slider(minimum=0, maximum=3, step=0.1, label="expression scale", value=1) # 
+                                pose_style = gr.Slider(minimum=0, maximum=45, step=1, label="Pose style", value=0)
+                                exp_weight = gr.Slider(minimum=0, maximum=3, step=0.1, label="expression scale", value=1)
                                 blink_every = gr.Checkbox(label="use eye blink", value=True)
 
                             with gr.Row():
-                                size_of_image = gr.Radio([256, 512], value=256, label='face model resolution', info="use 256/512 model?") # 
+                                size_of_image = gr.Radio([256, 512], value=256, label='face model resolution', info="use 256/512 model?")
                                 preprocess_type = gr.Radio(['crop', 'resize','full', 'extcrop', 'extfull'], value='crop', label='preprocess', info="How to handle input image?")
-                            
+
                             with gr.Row():
                                 is_still_mode = gr.Checkbox(label="Still Mode (fewer head motion, works with preprocess `full`)")
                                 facerender = gr.Radio(['facevid2vid','pirender'], value='facevid2vid', label='facerender', info="which face render?")
-                                
+
                             with gr.Row():
                                 batch_size = gr.Slider(label="batch size in generation", step=1, maximum=10, value=1)
                                 enhancer = gr.Checkbox(label="GFPGAN as Face enhancer")
-                            
+
                             submit = gr.Button('Generate', elem_id="sadtalker_generate", variant='primary')
-                            
-                with gr.Tabs(elem_id="sadtalker_genearted"):
-                        gen_video = gr.Video(label="Generated video", format="mp4", scale=1) # .style(width=256)
 
-        
+                with gr.Tabs(elem_id="sadtalker_genearted"):
+                    gen_video = gr.Video(label="Generated video", format="mp4", scale=1)
 
         submit.click(
-                fn=sad_talker.test,
-                inputs=[source_image,
-                        driven_audio,
-                        preprocess_type,
-                        is_still_mode,
-                        enhancer,
-                        batch_size,                            
-                        size_of_image,
-                        pose_style,
-                        facerender,
-                        exp_weight,
-                        use_ref_video,
-                        ref_video,
-                        ref_info,
-                        use_idle_mode,
-                        length_of_audio,
-                        blink_every
-                        ], 
-                outputs=[gen_video],
-                )
+            fn=sad_talker.test,
+            inputs=[source_image,
+                    driven_audio,
+                    preprocess_type,
+                    is_still_mode,
+                    enhancer,
+                    batch_size,
+                    size_of_image,
+                    pose_style,
+                    facerender,
+                    exp_weight,
+                    use_ref_video,
+                    ref_video,
+                    ref_info,
+                    use_idle_mode,
+                    length_of_audio,
+                    blink_every
+                    ],
+            outputs=[gen_video],
+        )
 
         with gr.Row():
             examples = [
@@ -201,18 +194,14 @@ def sadtalker_demo():
                             driven_audio,
                             preprocess_type,
                             is_still_mode,
-                            enhancer], 
+                            enhancer],
                         outputs=[gen_video],
                         fn=sad_talker.test,
-                        cache_examples=os.getenv('SYSTEM') == 'spaces') # 
+                        cache_examples=os.getenv('SYSTEM') == 'spaces')
 
     return sadtalker_interface
- 
 
 if __name__ == "__main__":
-
     demo = sadtalker_demo()
     demo.queue(max_size=10, api_open=True)
     demo.launch(debug=True)
-
-