Update app_multi.py

app_multi.py

@@ -793,86 +793,52 @@ with app:
                             with gr.Row():
                                 source_image = gr.Image(label="请上传一张您喜欢角色的图片", source="upload", type="filepath", elem_id="img2img_image").style(width=512)
         
-        
                     with gr.Tabs(elem_id="sadtalker_driven_audio"):
-                        with gr.TabItem('💡 完整视频'):
-
+                        with gr.TabItem():
+                            with gr.Column(variant='panel'):
+                                driven_audio = output_audio
+                                
                             submit = gr.Button('想把我唱给你听', elem_id="sadtalker_generate", variant='primary')
 
                             gen_mv = gr.Button('为视频添加伴奏吧', variant='primary')
 
-                            music_video = gr.Video(label="视频+伴奏", format="mp4").style(width=256)
-        
                             with gr.Row():
-                                driven_audio = output_audio
-                                driven_audio_no = gr.Audio(label="Use IDLE mode, no audio is required", source="upload", type="filepath", visible=False)
-        
-                                with gr.Column():
-                                    use_idle_mode = gr.Checkbox(label="Use Idle Animation", visible=False)
-                                    length_of_audio = gr.Number(value=5, label="The length(seconds) of the generated video.", visible=False)
-                                    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", source="upload", type="filepath", elem_id="vidref", visible=False).style(width=512)
-        
-                                with gr.Column():
-                                    use_ref_video = gr.Checkbox(label="Use Reference Video", visible=False)
-                                    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))", visible=False)
-        
-                                ref_video.change(ref_video_fn, inputs=ref_video, outputs=[use_ref_video]) # todo
-        
-        
-                with gr.Column(variant='panel'):
+                            
+                                gen_video = gr.Video(label="AI歌手数字人视频", format="mp4").style(width=256)
+
+                                music_video = gr.Video(label="视频+伴奏", format="mp4").style(width=256)
+      
+                with gr.Column(variant='panel'): 
                     with gr.Tabs(elem_id="sadtalker_checkbox"):
                         with gr.TabItem('视频设置'):
                             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, visible=False) #
-                                    exp_weight = gr.Slider(minimum=0, maximum=3, step=0.1, label="expression scale", value=1, visible=False) #
-                                    blink_every = gr.Checkbox(label="use eye blink", value=True, visible=False)
-        
-                                with gr.Row():
-                                    size_of_image = gr.Radio([256, 512], value=256, label='face model resolution', info="use 256/512 model?", visible=False) #
-                                    preprocess_type = gr.Radio(['crop', 'full'], value='crop', label='是否聚焦角色面部', info="crop：视频会聚焦角色面部；full：视频会显示图片全貌")
-        
-                                with gr.Row():
-                                    is_still_mode = gr.Checkbox(label="静态模式 (开启静态模式，角色的面部动作会减少；默认开启)", value=True)
-                                    facerender = gr.Radio(['facevid2vid','pirender'], value='facevid2vid', label='facerender', info="which face render?", visible=False)
-        
-                                with gr.Row():
-                                    batch_size = gr.Slider(label="Batch size (数值越大，生成速度越快；若显卡性能好，可增大数值)", step=1, maximum=32, value=2)
-                                    enhancer = gr.Checkbox(label="GFPGAN as Face enhancer", value=True, visible=False)
-        
-        
-                    with gr.Tabs(elem_id="sadtalker_genearted"):
-                            gen_video = gr.Video(label="为您生成的专属���频", format="mp4").style(width=256)
+                                pose_style = gr.Slider(minimum=0, maximum=46, step=1, label="Pose style", value=0, visible=False) # 
+                                size_of_image = gr.Radio([256, 512], value=256, label='face model resolution', info="use 256/512 model?", visible=False) # 
+                                preprocess_type = gr.Radio(['crop', 'full'], value='crop', label='是否聚焦角色面部', info="crop：视频会聚焦角色面部；full：视频会显示图片全貌")
+                                is_still_mode = gr.Checkbox(label="静态模式 (开启静态模式，角色的面部动作会减少；默认开启)", value=True)
+                                batch_size = gr.Slider(label="Batch size (数值越大，生成速度越快；若显卡性能好，可增大数值)", step=1, maximum=32, value=4)
+                                enhancer = gr.Checkbox(label="GFPGAN as Face enhancer", visible=False)
+                                    
+
+            submit.click(
+                        fn=sad_talker.test, 
+                        inputs=[source_image,
+                                driven_audio,
+                                preprocess_type,
+                                is_still_mode,
+                                enhancer,
+                                batch_size,                            
+                                size_of_image,
+                                pose_style
+                                ], 
+                        outputs=[gen_video]
+                        )
         
             gen_mv.click(fn=combine_music, inputs=[gen_video, as_audio_no_vocals], outputs=[music_video])
         
-            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]
-                    )    
-                                            
+ 
     gr.Markdown("### <center>注意❗：请不要生成会对个人以及组织造成侵害的内容，此程序仅供科研、学习及个人娱乐使用。</center>")
     gr.Markdown("<center>🧸 - 如何使用此程序：填写视频网址和视频起止时间后，依次点击“提取声音文件吧”、“去除背景音吧”、“进行歌声转换吧！”、“加入歌曲伴奏吧！”四个按键即可。</center>")
     gr.HTML('''