better ui's (#2)

- better ui's (5bc4b4a47e2330029f30d5ac29f6c27f1765cca7)


Co-authored-by: Rico Ardiansyah <Hev832@users.noreply.huggingface.co>

app.py

@@ -39,7 +39,7 @@ def sadtalker_demo():
     sad_talker = SadTalker(lazy_load=True)
     # tts_talker = TTSTalker()
 
-    with gr.Blocks(analytics_enabled=False) as sadtalker_interface:
+    with gr.Blocks(analytics_enabled=False, theme="Hev832/Applio") 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> \
                     <a style='font-size:18px;color: #efefef' href='https://arxiv.org/abs/2211.12194'>Arxiv</a> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; \
                     <a style='font-size:18px;color: #efefef' href='https://sadtalker.github.io'>Homepage</a>  &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; \
@@ -59,57 +59,48 @@ def sadtalker_demo():
                             source_image = gr.Image(label="Source image", type="filepath", elem_id="img2img_image")
 
 
-                with gr.Tabs(elem_id="sadtalker_driven_audio"):
-                    with gr.TabItem('Driving Methods'):
+                    with gr.TabItem('Driving Methods',elem_id="sadtalker_driven_audio"):
                         gr.Markdown("Possible driving combinations: <br> 1. Audio only 2. Audio/IDLE Mode + Ref Video(pose, blink, pose+blink) 3. IDLE Mode only 4. Ref Video only (all) ")
-
                         with gr.Row():
                             driven_audio = gr.Audio(label="Input audio", type="filepath")
                             driven_audio_no = gr.Audio(label="Use IDLE mode, no audio is required", type="filepath", visible=False)
-
-                            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
-
+                        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                      
                         with gr.Row():
-                            ref_video = gr.Video(label="Reference Video", elem_id="vidref")
+                             ref_video = gr.Video(label="Reference Video", 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))")
+                        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]) # todo
 
 
-            with gr.Column(variant='panel'): 
-                with gr.Tabs(elem_id="sadtalker_checkbox"):
-                    with gr.TabItem('Settings'):
+            
+                    with gr.TabItem('Settings',elem_id="sadtalker_checkbox"):
                         gr.Markdown("need help? please visit our [[best practice page](https://github.com/OpenTalker/SadTalker/blob/main/docs/best_practice.md)] for more detials")
                         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) # 
                                 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?") # 
-                                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")
+                        with gr.Row():
+                            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')
+                        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")
+                    gen_video = gr.Video(label="Generated video", format="mp4")
 
         
 
@@ -222,4 +213,4 @@ if __name__ == "__main__":
     demo.queue()
     demo.launch()
     #demo.queue(max_size=10, api_open=True)
-    #demo.launch(debug=True)
+    #demo.launch(debug=True)