Update easyanimate/ui/ui.py

easyanimate/ui/ui.py

@@ -673,12 +673,12 @@ def ui(GPU_memory_mode, weight_dtype):
         with gr.Column(variant="panel"):
             gr.Markdown(
                 """
-                ### 1. EasyAnimate Model Type (EasyAnimate模型的种类，正常模型还是控制模型).
+                ### 1. EasyAnimate Model Type ().
                 """
             )
             with gr.Row():
                 model_type = gr.Dropdown(
-                    label="The model type of EasyAnimate (EasyAnimate模型的种类，正常模型还是控制模型)",
+                    label="The model type of EasyAnimate ()",
                     choices=["Inpaint", "Control"],
                     value="Inpaint",
                     interactive=True,
@@ -691,7 +691,7 @@ def ui(GPU_memory_mode, weight_dtype):
             )
             with gr.Row():
                 easyanimate_edition_dropdown = gr.Dropdown(
-                    label="The config of EasyAnimate Edition (EasyAnimate版本配置)",
+                    label="The config of EasyAnimate Edition )",
                     choices=["v1", "v2", "v3", "v4", "v5", "v5.1"],
                     value="v5.1",
                     interactive=True,
@@ -703,7 +703,7 @@ def ui(GPU_memory_mode, weight_dtype):
             )
             with gr.Row():
                 diffusion_transformer_dropdown = gr.Dropdown(
-                    label="Pretrained Model Path (预训练模型路径)",
+                    label="Pretrained Model Path ()",
                     choices=controller.diffusion_transformer_list,
                     value="none",
                     interactive=True,
@@ -722,7 +722,7 @@ def ui(GPU_memory_mode, weight_dtype):
 
             with gr.Row():
                 motion_module_dropdown = gr.Dropdown(
-                    label="Select motion module (选择运动模块[非必需])",
+                    label="Select motion module ([])",
                     choices=controller.motion_module_list,
                     value="none",
                     interactive=True,
@@ -736,7 +736,7 @@ def ui(GPU_memory_mode, weight_dtype):
                 motion_module_refresh_button.click(fn=update_motion_module, inputs=[], outputs=[motion_module_dropdown])
                 
                 base_model_dropdown = gr.Dropdown(
-                    label="Select base Dreambooth model (选择基模型[非必需])",
+                    label="Select base Dreambooth model ([])",
                     choices=controller.personalized_model_list,
                     value="none",
                     interactive=True,
@@ -749,7 +749,7 @@ def ui(GPU_memory_mode, weight_dtype):
                     interactive=True,
                 )
 
-                lora_alpha_slider = gr.Slider(label="LoRA alpha (LoRA权重)", value=0.55, minimum=0, maximum=2, interactive=True)
+                lora_alpha_slider = gr.Slider(label="LoRA alpha ()", value=0.55, minimum=0, maximum=2, interactive=True)
                 
                 personalized_refresh_button = gr.Button(value="\U0001F503", elem_classes="toolbutton")
                 def update_personalized_model():
@@ -763,35 +763,35 @@ def ui(GPU_memory_mode, weight_dtype):
         with gr.Column(variant="panel"):
             gr.Markdown(
                 """
-                ### 3. Configs for Generation (生成参数配置).
+                ### 3. Configs for Generation ().
                 """
             )
             
-            prompt_textbox = gr.Textbox(label="Prompt (正向提示词)", lines=2, value="A young woman with beautiful, clear eyes and blonde hair stands in the forest, wearing a white dress and a crown. Her expression is serene, reminiscent of a movie star, with fair and youthful skin. Her brown long hair flows in the wind. The video quality is very high, with a clear view. High quality, masterpiece, best quality, high resolution, ultra-fine, fantastical.")
+            prompt_textbox = gr.Textbox(label="Prompt ()", lines=2, value="A young woman with beautiful, clear eyes and blonde hair stands in the forest, wearing a white dress and a crown. Her expression is serene, reminiscent of a movie star, with fair and youthful skin. Her brown long hair flows in the wind. The video quality is very high, with a clear view. High quality, masterpiece, best quality, high resolution, ultra-fine, fantastical.")
             gr.Markdown(
                 """
                 Using longer neg prompt such as "Blurring, mutation, deformation, distortion, dark and solid, comics, text subtitles, line art." can increase stability. Adding words such as "quiet, solid" to the neg prompt can increase dynamism.   
-                使用更长的neg prompt如"模糊，突变，变形，失真，画面暗，文本字幕，画面固定，连环画，漫画，线稿，没有主体。"，可以增加稳定性。在neg prompt中添加"安静，固定"等词语可以增加动态性。
+                
                 """
             )
-            negative_prompt_textbox = gr.Textbox(label="Negative prompt (负向提示词)", lines=2, value="Twisted body, limb deformities, text captions, comic, static, ugly, error, messy code." )
+            negative_prompt_textbox = gr.Textbox(label="Negative prompt ()", lines=2, value="Twisted body, limb deformities, text captions, comic, static, ugly, error, messy code." )
                 
             with gr.Row():
                 with gr.Column():
                     with gr.Row():
                         sampler_dropdown   = gr.Dropdown(
-                            label="Sampling method (采样器种类)", 
+                            label="Sampling method ()", 
                             choices=list(flow_scheduler_dict.keys()), value=list(flow_scheduler_dict.keys())[0]
                         )
-                        sample_step_slider = gr.Slider(label="Sampling steps (生成步数)", value=50, minimum=10, maximum=100, step=1)
+                        sample_step_slider = gr.Slider(label="Sampling steps ()", value=50, minimum=10, maximum=100, step=1)
                         
                     resize_method = gr.Radio(
                         ["Generate by", "Resize according to Reference"],
                         value="Generate by",
                         show_label=False,
                     )
-                    width_slider     = gr.Slider(label="Width (视频宽度)",            value=672, minimum=128, maximum=1344, step=16)
-                    height_slider    = gr.Slider(label="Height (视频高度)",           value=384, minimum=128, maximum=1344, step=16)
+                    width_slider     = gr.Slider(label="Width ()",            value=672, minimum=128, maximum=1344, step=16)
+                    height_slider    = gr.Slider(label="Height ()",           value=384, minimum=128, maximum=1344, step=16)
                     base_resolution  = gr.Radio(label="Base Resolution of Pretrained Models", value=512, choices=[512, 768, 960], visible=False)
 
                     with gr.Group():
@@ -801,18 +801,18 @@ def ui(GPU_memory_mode, weight_dtype):
                             show_label=False,
                         )
                         with gr.Row():
-                            length_slider = gr.Slider(label="Animation length (视频帧数)", value=49, minimum=1,   maximum=49,  step=4)
-                            overlap_video_length = gr.Slider(label="Overlap length (视频续写的重叠帧数)", value=4, minimum=1,   maximum=4,  step=1, visible=False)
-                            partial_video_length = gr.Slider(label="Partial video generation length (每个部分的视频生成帧数)", value=25, minimum=5,   maximum=49,  step=4, visible=False)
+                            length_slider = gr.Slider(label="Animation length ()", value=49, minimum=1,   maximum=49,  step=4)
+                            overlap_video_length = gr.Slider(label="Overlap length ()", value=4, minimum=1,   maximum=4,  step=1, visible=False)
+                            partial_video_length = gr.Slider(label="Partial video generation length ()", value=25, minimum=5,   maximum=49,  step=4, visible=False)
                     
                     source_method = gr.Radio(
-                        ["Text to Video (文本到视频)", "Image to Video (图片到视频)", "Video to Video (视频到视频)", "Video Control (视频控制)"],
-                        value="Text to Video (文本到视频)",
+                        ["Text to Video ()", "Image to Video (图片到视频)", "Video to Video ()", "Video Control (视频控制)"],
+                        value="Text to Video ()",
                         show_label=False,
                     )
                     with gr.Column(visible = False) as image_to_video_col:
                         start_image = gr.Image(
-                            label="The image at the beginning of the video (图片到视频的开始图片)",  show_label=True, 
+                            label="The image at the beginning of the video ()",  show_label=True, 
                             elem_id="i2v_start", sources="upload", type="filepath", 
                         )
                         
@@ -837,27 +837,27 @@ def ui(GPU_memory_mode, weight_dtype):
                         )
                         template_gallery.select(select_template, None, [start_image, prompt_textbox])
                         
-                        with gr.Accordion("The image at the ending of the video (图片到视频的结束图片[非必需, Optional])", open=False):
-                            end_image   = gr.Image(label="The image at the ending of the video (图片到视频的结束图片[非必需, Optional])", show_label=False, elem_id="i2v_end", sources="upload", type="filepath")
+                        with gr.Accordion("The image at the ending of the video ([, Optional])", open=False):
+                            end_image   = gr.Image(label="The image at the ending of the video ([, Optional])", show_label=False, elem_id="i2v_end", sources="upload", type="filepath")
 
                     with gr.Column(visible = False) as video_to_video_col:
                         with gr.Row():
                             validation_video = gr.Video(
-                                label="The video to convert (视频转视频的参考视频)",  show_label=True, 
+                                label="The video to convert ()",  show_label=True, 
                                 elem_id="v2v", sources="upload", 
                             )
-                        with gr.Accordion("The mask of the video to inpaint (视频重新绘制的mask[非必需, Optional])", open=False):
+                        with gr.Accordion("The mask of the video to inpaint ([, Optional])", open=False):
                             gr.Markdown(
                                 """
                                 - Please set a larger denoise_strength when using validation_video_mask, such as 1.00 instead of 0.70  
-                                - (请设置更大的denoise_strength，当使用validation_video_mask的时候，比如1而不是0.70)
+                                - (请设置更大的denoise_strength，，.70)
                                 """
                             )
                             validation_video_mask = gr.Image(
-                                label="The mask of the video to inpaint (视频重新绘制的mask[非必需, Optional])",
+                                label="The mask of the video to inpaint ([, Optional])",
                                 show_label=False, elem_id="v2v_mask", sources="upload", type="filepath"
                             )
-                        denoise_strength = gr.Slider(label="Denoise strength (重绘系数)", value=0.70, minimum=0.10, maximum=1.00, step=0.01)
+                        denoise_strength = gr.Slider(label="Denoise strength ()", value=0.70, minimum=0.10, maximum=1.00, step=0.01)
 
                     with gr.Column(visible = False) as control_video_col:
                         gr.Markdown(
@@ -867,14 +867,14 @@ def ui(GPU_memory_mode, weight_dtype):
                             """
                         )
                         control_video = gr.Video(
-                            label="The control video (用于提供控制信号的video)",  show_label=True, 
+                            label="The control video ()",  show_label=True, 
                             elem_id="v2v_control", sources="upload", 
                         )
 
-                    cfg_scale_slider  = gr.Slider(label="CFG Scale (引导系数)",        value=6.0, minimum=0,   maximum=20)
+                    cfg_scale_slider  = gr.Slider(label="CFG Scale ()",        value=6.0, minimum=0,   maximum=20)
                     
                     with gr.Row():
-                        seed_textbox = gr.Textbox(label="Seed (随机种子)", value=43)
+                        seed_textbox = gr.Textbox(label="Seed ()", value=43)
                         seed_button  = gr.Button(value="\U0001F3B2", elem_classes="toolbutton")
                         seed_button.click(
                             fn=lambda: gr.Textbox(value=random.randint(1, 1e8)) if gradio_version_is_above_4 else gr.Textbox.update(value=random.randint(1, 1e8)), 
@@ -882,11 +882,11 @@ def ui(GPU_memory_mode, weight_dtype):
                             outputs=[seed_textbox]
                         )
 
-                    generate_button = gr.Button(value="Generate (生成)", variant='primary')
+                    generate_button = gr.Button(value="Generate ()", variant='primary')
                     
                 with gr.Column():
-                    result_image = gr.Image(label="Generated Image (生成图片)", interactive=False, visible=False)
-                    result_video = gr.Video(label="Generated Animation (生成视频)", interactive=False)
+                    result_image = gr.Image(label="Generated Image ()", interactive=False, visible=False)
+                    result_video = gr.Video(label="Generated Animation ()", interactive=False)
                     infer_progress = gr.Textbox(
                         label="Generation Info (生成信息)",
                         value="No task currently",
@@ -921,11 +921,11 @@ def ui(GPU_memory_mode, weight_dtype):
             )
 
             def upload_source_method(source_method):
-                if source_method == "Text to Video (文本到视频)":
+                if source_method == "Text to Video ()":
                     return [gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update(value=None)]
-                elif source_method == "Image to Video (图片到视频)":
+                elif source_method == "Image to Video ()":
                     return [gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(), gr.update(), gr.update(value=None), gr.update(value=None), gr.update(value=None)]
-                elif source_method == "Video to Video (视频到视频)":
+                elif source_method == "Video to Video ()":
                     return [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False), gr.update(value=None), gr.update(value=None), gr.update(), gr.update(), gr.update(value=None)]
                 else:
                     return [gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update()]
@@ -1385,26 +1385,26 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
         with gr.Column(variant="panel"):
             gr.Markdown(
                 """
-                ### 1. Model checkpoints (模型路径).
+                ### 1. Model checkpoints ().
                 """
             )
             with gr.Row():
                 diffusion_transformer_dropdown = gr.Dropdown(
-                    label="Pretrained Model Path (预训练模型路径)",
+                    label="Pretrained Model Path ()",
                     choices=[model_name],
                     value=model_name,
                     interactive=False,
                 )
             with gr.Row():
                 motion_module_dropdown = gr.Dropdown(
-                    label="Select motion module (选择运动模块[非必需])",
+                    label="Select motion module ([])",
                     choices=["none"],
                     value="none",
                     interactive=False,
                     visible=False
                 )
                 base_model_dropdown = gr.Dropdown(
-                    label="Select base Dreambooth model (选择基模型[非必需])",
+                    label="Select base Dreambooth model ([])",
                     choices=["none"],
                     value="none",
                     interactive=False,
@@ -1424,42 +1424,41 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
                             interactive=False,
                         )
 
-                        lora_alpha_slider = gr.Slider(label="LoRA alpha (LoRA权重)", value=0.55, minimum=0, maximum=2, interactive=True)
+                        lora_alpha_slider = gr.Slider(label="LoRA alpha ()", value=0.55, minimum=0, maximum=2, interactive=True)
                 
         with gr.Column(variant="panel"):
             gr.Markdown(
                 """
-                ### 2. Configs for Generation (生成参数配置).
+                ### 2. Configs for Generation ().
                 """
             )
 
-            prompt_textbox = gr.Textbox(label="Prompt (正向提示词)", lines=2, value="A young woman with beautiful, clear eyes and blonde hair stands in the forest, wearing a white dress and a crown. Her expression is serene, reminiscent of a movie star, with fair and youthful skin. Her brown long hair flows in the wind. The video quality is very high, with a clear view. High quality, masterpiece, best quality, high resolution, ultra-fine, fantastical.")
+            prompt_textbox = gr.Textbox(label="Prompt ()", lines=2, value="A young woman with beautiful, clear eyes and blonde hair stands in the forest, wearing a white dress and a crown. Her expression is serene, reminiscent of a movie star, with fair and youthful skin. Her brown long hair flows in the wind. The video quality is very high, with a clear view. High quality, masterpiece, best quality, high resolution, ultra-fine, fantastical.")
             gr.Markdown(
                 """
                 Using longer neg prompt such as "Blurring, mutation, deformation, distortion, dark and solid, comics, text subtitles, line art." can increase stability. Adding words such as "quiet, solid" to the neg prompt can increase dynamism.   
-                使用更长的neg prompt如"模糊，突变，变形，失真，画面暗，文本字幕，画面固定，连环画，漫画，线稿，没有主体。"，可以增加稳定性。在neg prompt中添加"安静，固定"等词语可以增加动态性。
                 """
             )
-            negative_prompt_textbox = gr.Textbox(label="Negative prompt (负向提示词)", lines=2, value="Twisted body, limb deformities, text captions, comic, static, ugly, error, messy code." )
+            negative_prompt_textbox = gr.Textbox(label="Negative prompt ()", lines=2, value="Twisted body, limb deformities, text captions, comic, static, ugly, error, messy code." )
                 
             with gr.Row():
                 with gr.Column():
                     with gr.Row():
                         if edition in ["v5.1"]:
                             sampler_dropdown   = gr.Dropdown(
-                                label="Sampling method (采样器种类)", 
+                                label="Sampling method ()", 
                                 choices=list(flow_scheduler_dict.keys()), value=list(flow_scheduler_dict.keys())[0]
                             )
                         else:
                             sampler_dropdown   = gr.Dropdown(
-                                label="Sampling method (采样器种类)", 
+                                label="Sampling method ()", 
                                 choices=list(ddpm_scheduler_dict.keys()), value=list(ddpm_scheduler_dict.keys())[0]
                             )
-                        sample_step_slider = gr.Slider(label="Sampling steps (生成步数)", value=50, minimum=10, maximum=50, step=1, interactive=False)
+                        sample_step_slider = gr.Slider(label="Sampling steps ()", value=50, minimum=10, maximum=50, step=1, interactive=False)
                     
                     if edition == "v1":
-                        width_slider     = gr.Slider(label="Width (视频宽度)",            value=512, minimum=384, maximum=704, step=32)
-                        height_slider    = gr.Slider(label="Height (视频高度)",           value=512, minimum=384, maximum=704, step=32)
+                        width_slider     = gr.Slider(label="Width ()",            value=512, minimum=384, maximum=704, step=32)
+                        height_slider    = gr.Slider(label="Height ()",           value=512, minimum=384, maximum=704, step=32)
 
                         with gr.Group():
                             generation_method = gr.Radio(
@@ -1468,18 +1467,18 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
                                 show_label=False,
                                 visible=False,
                             )
-                            length_slider = gr.Slider(label="Animation length (视频帧数)", value=80,  minimum=40,  maximum=96,   step=1)
-                        overlap_video_length = gr.Slider(label="Overlap length (视频续写的重叠帧数)", value=4, minimum=1,   maximum=4,  step=1, visible=False)
-                        partial_video_length = gr.Slider(label="Partial video generation length (每个部分的视频生成帧数)", value=72, minimum=8,   maximum=144,  step=8, visible=False)
-                        cfg_scale_slider = gr.Slider(label="CFG Scale (引导系数)",        value=6.0, minimum=0,   maximum=20)
+                            length_slider = gr.Slider(label="Animation length ()", value=80,  minimum=40,  maximum=96,   step=1)
+                        overlap_video_length = gr.Slider(label="Overlap length ()", value=4, minimum=1,   maximum=4,  step=1, visible=False)
+                        partial_video_length = gr.Slider(label="Partial video generation length ()", value=72, minimum=8,   maximum=144,  step=8, visible=False)
+                        cfg_scale_slider = gr.Slider(label="CFG Scale ()",        value=6.0, minimum=0,   maximum=20)
                     else:
                         resize_method = gr.Radio(
                             ["Generate by", "Resize according to Reference"],
                             value="Generate by",
                             show_label=False,
                         )
-                        width_slider     = gr.Slider(label="Width (视频宽度)",            value=672, minimum=128, maximum=1344, step=16, interactive=False)
-                        height_slider    = gr.Slider(label="Height (视频高度)",           value=384, minimum=128, maximum=1344, step=16, interactive=False)
+                        width_slider     = gr.Slider(label="Width ()",            value=672, minimum=128, maximum=1344, step=16, interactive=False)
+                        height_slider    = gr.Slider(label="Height ()",           value=384, minimum=128, maximum=1344, step=16, interactive=False)
                         base_resolution  = gr.Radio(label="Base Resolution of Pretrained Models", value=512, choices=[512, 768, 960], interactive=False, visible=False)
 
                         with gr.Group():
@@ -1490,20 +1489,20 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
                                 visible=True,
                             )
                             if edition in ["v2", "v3", "v4"]:
-                                length_slider = gr.Slider(label="Animation length (视频帧数)", value=144, minimum=8,   maximum=144,  step=8)
+                                length_slider = gr.Slider(label="Animation length ()", value=144, minimum=8,   maximum=144,  step=8)
                             else:
-                                length_slider = gr.Slider(label="Animation length (视频帧数)", value=49, minimum=5,   maximum=49,  step=4)
-                            overlap_video_length = gr.Slider(label="Overlap length (视频续写的重叠帧数)", value=4, minimum=1,   maximum=4,  step=1, visible=False)
-                            partial_video_length = gr.Slider(label="Partial video generation length (每个部分的视频生成帧数)", value=72, minimum=8,   maximum=144,  step=8, visible=False)
+                                length_slider = gr.Slider(label="Animation length ()", value=49, minimum=5,   maximum=49,  step=4)
+                            overlap_video_length = gr.Slider(label="Overlap length ()", value=4, minimum=1,   maximum=4,  step=1, visible=False)
+                            partial_video_length = gr.Slider(label="Partial video generation length ()", value=72, minimum=8,   maximum=144,  step=8, visible=False)
                         
                         source_method = gr.Radio(
-                            ["Text to Video (文本到视频)", "Image to Video (图片到视频)", "Video to Video (视频到视频)", "Video Control (视频控制)"],
-                            value="Text to Video (文本到视频)",
+                            ["Text to Video ()", "Image to Video ()", "Video to Video ()", "Video Control ()"],
+                            value="Text to Video ()",
                             show_label=False,
                         )
                         with gr.Column(visible = False) as image_to_video_col:
                             with gr.Row():
-                                start_image = gr.Image(label="The image at the beginning of the video (图片到视频的开始图片)", show_label=True, elem_id="i2v_start", sources="upload", type="filepath")
+                                start_image = gr.Image(label="The image at the beginning of the video ()", show_label=True, elem_id="i2v_start", sources="upload", type="filepath")
                             
                             template_gallery_path = ["asset/1.png", "asset/2.png", "asset/3.png", "asset/4.png", "asset/5.png"]
                             def select_template(evt: gr.SelectData):
@@ -1526,27 +1525,27 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
                             )
                             template_gallery.select(select_template, None, [start_image, prompt_textbox])
 
-                            with gr.Accordion("The image at the ending of the video (图片到视频的结束图片[非必需, Optional])", open=False):
-                                end_image   = gr.Image(label="The image at the ending of the video (图片到视频的结束图片[非必需, Optional])", show_label=False, elem_id="i2v_end", sources="upload", type="filepath")
+                            with gr.Accordion("The image at the ending of the video ([, Optional])", open=False):
+                                end_image   = gr.Image(label="The image at the ending of the video ([, Optional])", show_label=False, elem_id="i2v_end", sources="upload", type="filepath")
 
                         with gr.Column(visible = False) as video_to_video_col:
                             with gr.Row():
                                 validation_video = gr.Video(
-                                    label="The video to convert (视频转视频的参考视频)",  show_label=True, 
+                                    label="The video to convert ()",  show_label=True, 
                                     elem_id="v2v", sources="upload", 
                                 ) 
-                            with gr.Accordion("The mask of the video to inpaint (视频重新绘制的mask[非必需, Optional])", open=False):
+                            with gr.Accordion("The mask of the video to inpaint (, Optional])", open=False):
                                 gr.Markdown(
                                     """
                                     - Please set a larger denoise_strength when using validation_video_mask, such as 1.00 instead of 0.70  
-                                    - (请设置更大的denoise_strength，当使用validation_video_mask的时候，比如1而不是0.70)
+                                    - (，，.70)
                                     """
                                 )
                                 validation_video_mask = gr.Image(
-                                    label="The mask of the video to inpaint (视频重新绘制的mask[非必需, Optional])",
+                                    label="The mask of the video to inpaint ([, Optional])",
                                     show_label=False, elem_id="v2v_mask", sources="upload", type="filepath"
                                 )
-                            denoise_strength = gr.Slider(label="Denoise strength (重绘系数)", value=0.70, minimum=0.10, maximum=1.00, step=0.01)
+                            denoise_strength = gr.Slider(label="Denoise strength ()", value=0.70, minimum=0.10, maximum=1.00, step=0.01)
 
                         with gr.Column(visible = False) as control_video_col:
                             gr.Markdown(
@@ -1556,14 +1555,14 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
                                 """
                             )
                             control_video = gr.Video(
-                                label="The control video (用于提供控制信号的video)",  show_label=True, 
+                                label="The control video ()",  show_label=True, 
                                 elem_id="v2v_control", sources="upload", 
                             )
 
-                    cfg_scale_slider  = gr.Slider(label="CFG Scale (引导系数)",        value=6.0, minimum=0,   maximum=20)
+                    cfg_scale_slider  = gr.Slider(label="CFG Scale ()",        value=6.0, minimum=0,   maximum=20)
                     
                     with gr.Row():
-                        seed_textbox = gr.Textbox(label="Seed (随机种子)", value=43)
+                        seed_textbox = gr.Textbox(label="Seed ()", value=43)
                         seed_button  = gr.Button(value="\U0001F3B2", elem_classes="toolbutton")
                         seed_button.click(
                             fn=lambda: gr.Textbox(value=random.randint(1, 1e8)) if gradio_version_is_above_4 else gr.Textbox.update(value=random.randint(1, 1e8)), 
@@ -1571,13 +1570,13 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
                             outputs=[seed_textbox]
                         )
 
-                    generate_button = gr.Button(value="Generate (生成)", variant='primary')
+                    generate_button = gr.Button(value="Generate ()", variant='primary')
                     
                 with gr.Column():
-                    result_image = gr.Image(label="Generated Image (生成图片)", interactive=False, visible=False)
-                    result_video = gr.Video(label="Generated Animation (生成视频)", interactive=False)
+                    result_image = gr.Image(label="Generated Image ()", interactive=False, visible=False)
+                    result_video = gr.Video(label="Generated Animation ()", interactive=False)
                     infer_progress = gr.Textbox(
-                        label="Generation Info (生成信息)",
+                        label="Generation Info ()",
                         value="No task currently",
                         interactive=False
                     )
@@ -1602,11 +1601,11 @@ def ui_modelscope(model_type, edition, config_path, model_name, savedir_sample,
             )
 
             def upload_source_method(source_method):
-                if source_method == "Text to Video (文本到视频)":
+                if source_method == "Text to Video )":
                     return [gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update(value=None)]
-                elif source_method == "Image to Video (图片到视频)":
+                elif source_method == "Image to Video )":
                     return [gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(), gr.update(), gr.update(value=None), gr.update(value=None), gr.update(value=None)]
-                elif source_method == "Video to Video (视频到视频)":
+                elif source_method == "Video to Video )":
                     return [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False), gr.update(value=None), gr.update(value=None), gr.update(), gr.update(), gr.update(value=None)]
                 else:
                     return [gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update()]
@@ -1854,7 +1853,7 @@ def ui_eas(edition, config_path, model_name, savedir_sample):
                             interactive=False,
                         )
 
-                        lora_alpha_slider = gr.Slider(label="LoRA alpha (LoRA权重)", value=0.55, minimum=0, maximum=2, interactive=True)
+                        lora_alpha_slider = gr.Slider(label="LoRA alpha ()", value=0.55, minimum=0, maximum=2, interactive=True)
                 
         with gr.Column(variant="panel"):
             gr.Markdown(
@@ -1867,7 +1866,6 @@ def ui_eas(edition, config_path, model_name, savedir_sample):
             gr.Markdown(
                 """
                 Using longer neg prompt such as "Blurring, mutation, deformation, distortion, dark and solid, comics, text subtitles, line art." can increase stability. Adding words such as "quiet, solid" to the neg prompt can increase dynamism.   
-                使用更长的neg prompt如"模糊，突变，变形，失真，画面暗，文本字幕，画面固定，连环画，漫画，线稿，没有主体。"，可以增加稳定性。在neg prompt中添加"安静，固定"等词语可以增加动态性。
                 """
             )
             negative_prompt_textbox = gr.Textbox(label="Negative prompt", lines=2, value="Twisted body, limb deformities, text captions, comic, static, ugly, error, messy code." )
@@ -1877,12 +1875,12 @@ def ui_eas(edition, config_path, model_name, savedir_sample):
                     with gr.Row():
                         if edition in ["v5.1"]:
                             sampler_dropdown   = gr.Dropdown(
-                                label="Sampling method (采样器种类)", 
+                                label="Sampling method ()", 
                                 choices=list(flow_scheduler_dict.keys()), value=list(flow_scheduler_dict.keys())[0]
                             )
                         else:
                             sampler_dropdown   = gr.Dropdown(
-                                label="Sampling method (采样器种类)", 
+                                label="Sampling method ()", 
                                 choices=list(ddpm_scheduler_dict.keys()), value=list(ddpm_scheduler_dict.keys())[0]
                             )
                         sample_step_slider = gr.Slider(label="Sampling steps", value=40, minimum=10, maximum=40, step=1, interactive=False)
@@ -1906,8 +1904,8 @@ def ui_eas(edition, config_path, model_name, savedir_sample):
                             value="Generate by",
                             show_label=False,
                         )
-                        width_slider     = gr.Slider(label="Width (视频宽度)",            value=672, minimum=128, maximum=1344, step=16, interactive=False)
-                        height_slider    = gr.Slider(label="Height (视频高度)",           value=384, minimum=128, maximum=1344, step=16, interactive=False)
+                        width_slider     = gr.Slider(label="Width ()",            value=672, minimum=128, maximum=1344, step=16, interactive=False)
+                        height_slider    = gr.Slider(label="Height ()",           value=384, minimum=128, maximum=1344, step=16, interactive=False)
                         base_resolution  = gr.Radio(label="Base Resolution of Pretrained Models", value=512, choices=[512, 768, 960], interactive=False, visible=False)
 
                         with gr.Group():
@@ -1918,13 +1916,13 @@ def ui_eas(edition, config_path, model_name, savedir_sample):
                                 visible=True,
                             )
                             if edition in ["v2", "v3", "v4"]:
-                                length_slider = gr.Slider(label="Animation length (视频帧数)", value=144, minimum=8,   maximum=144,  step=8)
+                                length_slider = gr.Slider(label="Animation length ()", value=144, minimum=8,   maximum=144,  step=8)
                             else:
-                                length_slider = gr.Slider(label="Animation length (视频帧数)", value=21, minimum=5,   maximum=21,  step=4)
+                                length_slider = gr.Slider(label="Animation length ()", value=21, minimum=5,   maximum=21,  step=4)
                         
                         source_method = gr.Radio(
-                            ["Text to Video (文本到视频)", "Image to Video (图片到视频)", "Video to Video (视频到视频)"],
-                            value="Text to Video (文本到视频)",
+                            ["Text to Video ()", "Image to Video ()", "Video to Video ()"],
+                            value="Text to Video ()",
                             show_label=False,
                         )
                         with gr.Column(visible = False) as image_to_video_col:
@@ -1957,23 +1955,22 @@ def ui_eas(edition, config_path, model_name, savedir_sample):
                         with gr.Column(visible = False) as video_to_video_col:
                             with gr.Row():
                                 validation_video = gr.Video(
-                                    label="The video to convert (视频转视频的参考视频)",  show_label=True, 
+                                    label="The video to convert ()",  show_label=True, 
                                     elem_id="v2v", sources="upload", 
                                 )
-                            with gr.Accordion("The mask of the video to inpaint (视频重新绘制的mask[非必需, Optional])", open=False):
+                            with gr.Accordion("The mask of the video to inpaint ([, Optional])", open=False):
                                 gr.Markdown(
                                     """
                                     - Please set a larger denoise_strength when using validation_video_mask, such as 1.00 instead of 0.70  
-                                    - (请设置更大的denoise_strength，当使用validation_video_mask的时候，比如1而不是0.70)
                                     """
                                 )
                                 validation_video_mask = gr.Image(
-                                    label="The mask of the video to inpaint (视频重新绘制的mask[非必需, Optional])",
+                                    label="The mask of the video to inpaint ([, Optional])",
                                     show_label=False, elem_id="v2v_mask", sources="upload", type="filepath"
                                 )
-                            denoise_strength = gr.Slider(label="Denoise strength (重绘系数)", value=0.70, minimum=0.10, maximum=1.00, step=0.01)
+                            denoise_strength = gr.Slider(label="Denoise strength ()", value=0.70, minimum=0.10, maximum=1.00, step=0.01)
 
-                        cfg_scale_slider  = gr.Slider(label="CFG Scale (引导系数)",        value=6.0, minimum=0,   maximum=20)
+                        cfg_scale_slider  = gr.Slider(label="CFG Scale ()",        value=6.0, minimum=0,   maximum=20)
 
                     with gr.Row():
                         seed_textbox = gr.Textbox(label="Seed", value=43)
@@ -2015,9 +2012,9 @@ def ui_eas(edition, config_path, model_name, savedir_sample):
             )
 
             def upload_source_method(source_method):
-                if source_method == "Text to Video (文本到视频)":
+                if source_method == "Text to Video ()":
                     return [gr.update(visible=False), gr.update(visible=False), gr.update(value=None), gr.update(value=None), gr.update(value=None), gr.update(value=None)]
-                elif source_method == "Image to Video (图片到视频)":
+                elif source_method == "Image to Video ()":
                     return [gr.update(visible=True), gr.update(visible=False), gr.update(), gr.update(), gr.update(value=None), gr.update(value=None)]
                 else:
                     return [gr.update(visible=False), gr.update(visible=True), gr.update(value=None), gr.update(value=None), gr.update(), gr.update()]