Updated packages and requirements, added device print statement, modified README, added webui.bat and test.sh scripts, and downloaded new models and enhancer weights.

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +32,21 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoints/BFM_Fitting/01_MorphableModel.mat filter=lfs diff=lfs merge=lfs -text
+checkpoints/BFM_Fitting/BFM09_model_info.mat filter=lfs diff=lfs merge=lfs -text
+checkpoints/facevid2vid_00189-model.pth.tar filter=lfs diff=lfs merge=lfs -text
+checkpoints/mapping_00229-model.pth.tar filter=lfs diff=lfs merge=lfs -text
+checkpoints/shape_predictor_68_face_landmarks.dat filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/chinese_news.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/deyu.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/eluosi.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/fayu.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/imagine.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/japanese.wav filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_16.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_17.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_3.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_4.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_5.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_8.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_9.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,13 @@
 ---
 title: AvatarTest
-emoji: 🔥
-colorFrom: blue
-colorTo: indigo
+emoji: 😭
+colorFrom: purple
+colorTo: green
 sdk: gradio
-sdk_version: 4.19.2
+sdk_version: 3.23.0
 app_file: app.py
 pinned: false
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,5 +1,7 @@
 import os, sys
+import uuid
 import tempfile
+import pyttsx3
 import gradio as gr
 from src.gradio_demo import SadTalker  
 # from src.utils.text2speech import TTSTalker
@@ -28,8 +30,88 @@ def ref_video_fn(path_of_ref_video):
         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)
+     REPO_ID = 'vinthony/SadTalker-V002rc'
+     snapshot_download(REPO_ID)
+
+# language  : en_US, de_DE, ...
+# gender    : VoiceGenderFemale, VoiceGenderMale
+def change_voice(engine, language='ru_ru', gender='male'):
+
+    selected_voices = []
+    
+    language = language.lower() if language else ''
+    gender = gender.lower() if gender else ''
+
+    for voice in engine.getProperty('voices'):
+        voice_appended = False
+
+        for lang in voice.languages:
+            
+            lang_str = str(lang, 'utf-8')
+            print("lang", lang_str)
+            
+            if lang_str and language in lang_str.lower():
+                selected_voices.append(voice)
+                print("voice appended by lang", voice, lang_str)
+                voice_appended = True
+                break
+
+        if voice_appended:
+            continue
+
+        if voice.id and language in voice.id.lower():
+            selected_voices.append(voice)
+            print("voice appended by id", voice.id)
+            continue
+
+        if voice.name and language in voice.name.lower():
+            selected_voices.append(voice)
+            print("voice appended by name", voice.name)
+            continue
+
+    for voice in selected_voices:
+        if voice.gender and gender in voice.gender.lower():
+            engine.setProperty('voice', voice.id)
+            print("voice selected by gender", voice.gender)
+            return True
+    
+        if voice.id and gender in voice.id.lower():
+            engine.setProperty('voice', voice.id)
+            print("voice selected by id", voice.id)
+            return True
+        if voice.name and gender in voice.name.lower():
+            engine.setProperty('voice', voice.id)
+            print("voice selected by name", voice.name)
+            return True
+
+    if len(selected_voices) > 0:
+        engine.setProperty('voice', selected_voices[0].id)
+        print("voice selected by default", selected_voices[0].id)
+        return True
+    
+    return False
+
+def play_text_to_speech(text_input, voice_option):
+    engine = pyttsx3.init()
+    
+    change_voice(engine, 'ru', voice_option)
+
+    print("text_input", text_input)
+    print("voice_option", voice_option)
+   
+    time_tag = str(uuid.uuid4())
+    save_dir = './results/voice_input'
+    os.makedirs(save_dir, exist_ok=True)
+    file_name = os.path.join(save_dir, os.path.basename(time_tag + '.wav')) 
+    
+    open(file_name, "wb").close()
+    engine.say(text_input)
+    engine.save_to_file(text_input, file_name)
+    engine.runAndWait()
+    
+    print("file saved to", file_name)
+
+    return file_name
 
 def sadtalker_demo():
 
@@ -38,41 +120,37 @@ def sadtalker_demo():
     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> \
-                    <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; \
-                     <a style='font-size:18px;color: #efefef' href='https://github.com/Winfredy/SadTalker'> Github </div>")
-        
-        
-        gr.Markdown("""
-        <b>You may duplicate the space and upgrade to GPU in settings for better performance and faster inference without waiting in the queue. <a style='display:inline-block' href="https://huggingface.co/spaces/vinthony/SadTalker?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a></b> \
-        <br/><b>Alternatively, try our GitHub <a href=https://github.com/Winfredy/SadTalker> code </a> on your own GPU. </b> <a style='display:inline-block' href="https://github.com/Winfredy/SadTalker"><img src="https://img.shields.io/github/stars/Winfredy/SadTalker?style=social"/></a> \
-        """)
-        
-        with gr.Row().style(equal_height=False):
+    with gr.Blocks(analytics_enabled=False) as sadtalker_interface: 
+        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'):
-                        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", source="upload", type="filepath")
                             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")
+                            with gr.Column(visible=False):
+                                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.")
                                 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").style(width=512)
+                            text_input = gr.Textbox(label="Enter text", multiline=True)
+                            voice_option = gr.Radio(['Male', 'Female'], label='Voice Option', value='Female')
+                        with gr.Row():
+                            play_button = gr.Button('Text To Speech', variant='primary')
+                            play_button.click(
+                                fn=play_text_to_speech,
+                                inputs=[text_input, voice_option],
+                                outputs=[driven_audio]
+                            ) 
+                        with gr.Row():
+                            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")
@@ -84,7 +162,6 @@ def sadtalker_demo():
             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")
                         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
@@ -108,7 +185,7 @@ def sadtalker_demo():
                             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").style(width=256)
+                        gen_video = gr.Video(label="Generated video", format="mp4")
 
         
 
@@ -132,84 +209,7 @@ def sadtalker_demo():
                         blink_every
                         ], 
                 outputs=[gen_video]
-                )
-
-        with gr.Row():
-            examples = [
-                [
-                    'examples/source_image/full_body_1.png',
-                    'examples/driven_audio/bus_chinese.wav',
-                    'crop',
-                    True,
-                    False
-                ],
-                [
-                    'examples/source_image/full_body_2.png',
-                    'examples/driven_audio/japanese.wav',
-                    'crop',
-                    False,
-                    False
-                ],
-                [
-                    'examples/source_image/full3.png',
-                    'examples/driven_audio/deyu.wav',
-                    'crop',
-                    False,
-                    True
-                ],
-                [
-                    'examples/source_image/full4.jpeg',
-                    'examples/driven_audio/eluosi.wav',
-                    'full',
-                    False,
-                    True
-                ],
-                [
-                    'examples/source_image/full4.jpeg',
-                    'examples/driven_audio/imagine.wav',
-                    'full',
-                    True,
-                    True
-                ],
-                [
-                    'examples/source_image/full_body_1.png',
-                    'examples/driven_audio/bus_chinese.wav',
-                    'full',
-                    True,
-                    False
-                ],
-                [
-                    'examples/source_image/art_13.png',
-                    'examples/driven_audio/fayu.wav',
-                    'resize',
-                    True,
-                    False
-                ],
-                [
-                    'examples/source_image/art_5.png',
-                    'examples/driven_audio/chinese_news.wav',
-                    'resize',
-                    False,
-                    False
-                ],
-                [
-                    'examples/source_image/art_5.png',
-                    'examples/driven_audio/RD_Radio31_000.wav',
-                    'resize',
-                    True,
-                    True
-                ],
-            ]
-            gr.Examples(examples=examples,
-                        inputs=[
-                            source_image,
-                            driven_audio,
-                            preprocess_type,
-                            is_still_mode,
-                            enhancer], 
-                        outputs=[gen_video],
-                        fn=sad_talker.test,
-                        cache_examples=os.getenv('SYSTEM') == 'spaces') # 
+                ) 
 
     return sadtalker_interface
  

packages.txt

@@ -1,2 +1,3 @@
 ffmpeg
-libsndfile1
+libsndfile1
+libespeak1

requirements.txt

@@ -21,4 +21,5 @@ facexlib==0.3.0
 dlib-bin
 gfpgan
 av
-safetensors
+safetensors
+pyttsx3==2.90

scripts/download_models.sh

@@ -0,0 +1,32 @@
+mkdir ./checkpoints  
+
+# lagency download link
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/auido2exp_00300-model.pth -O ./checkpoints/auido2exp_00300-model.pth
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/auido2pose_00140-model.pth -O ./checkpoints/auido2pose_00140-model.pth
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/epoch_20.pth -O ./checkpoints/epoch_20.pth
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/facevid2vid_00189-model.pth.tar -O ./checkpoints/facevid2vid_00189-model.pth.tar
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/shape_predictor_68_face_landmarks.dat -O ./checkpoints/shape_predictor_68_face_landmarks.dat
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/wav2lip.pth -O ./checkpoints/wav2lip.pth
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/mapping_00229-model.pth.tar -O ./checkpoints/mapping_00229-model.pth.tar
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/mapping_00109-model.pth.tar -O ./checkpoints/mapping_00109-model.pth.tar
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/hub.zip -O ./checkpoints/hub.zip
+# unzip -n ./checkpoints/hub.zip -d ./checkpoints/
+
+
+#### download the new links.
+wget -nc https://github.com/OpenTalker/SadTalker/releases/download/v0.0.2-rc/mapping_00109-model.pth.tar -O  ./checkpoints/mapping_00109-model.pth.tar
+wget -nc https://github.com/OpenTalker/SadTalker/releases/download/v0.0.2-rc/mapping_00229-model.pth.tar -O  ./checkpoints/mapping_00229-model.pth.tar
+wget -nc https://github.com/OpenTalker/SadTalker/releases/download/v0.0.2-rc/SadTalker_V0.0.2_256.safetensors -O  ./checkpoints/SadTalker_V0.0.2_256.safetensors
+wget -nc https://github.com/OpenTalker/SadTalker/releases/download/v0.0.2-rc/SadTalker_V0.0.2_512.safetensors -O  ./checkpoints/SadTalker_V0.0.2_512.safetensors
+
+
+# wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.2/BFM_Fitting.zip -O ./checkpoints/BFM_Fitting.zip
+# unzip -n ./checkpoints/BFM_Fitting.zip -d ./checkpoints/
+
+### enhancer 
+mkdir -p ./gfpgan/weights
+wget -nc https://github.com/xinntao/facexlib/releases/download/v0.1.0/alignment_WFLW_4HG.pth -O ./gfpgan/weights/alignment_WFLW_4HG.pth 
+wget -nc https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth -O ./gfpgan/weights/detection_Resnet50_Final.pth 
+wget -nc https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -O ./gfpgan/weights/GFPGANv1.4.pth 
+wget -nc https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth -O ./gfpgan/weights/parsing_parsenet.pth 
+

scripts/extension.py

@@ -0,0 +1,189 @@
+import os, sys
+from pathlib import Path
+import tempfile
+import gradio as gr
+from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call
+from modules.shared import opts, OptionInfo
+from modules import shared, paths, script_callbacks
+import launch
+import glob
+from huggingface_hub import snapshot_download
+
+
+
+def check_all_files_safetensor(current_dir):
+    kv = {
+        "SadTalker_V0.0.2_256.safetensors": "sadtalker-256",
+        "SadTalker_V0.0.2_512.safetensors": "sadtalker-512",
+        "mapping_00109-model.pth.tar" : "mapping-109" ,
+        "mapping_00229-model.pth.tar" : "mapping-229" ,
+    }
+
+    if not os.path.isdir(current_dir):
+        return False
+    
+    dirs = os.listdir(current_dir)
+
+    for f in dirs:
+        if f in kv.keys():
+            del kv[f]
+
+    return len(kv.keys()) == 0
+
+def check_all_files(current_dir):
+    kv = {
+        "auido2exp_00300-model.pth": "audio2exp",
+        "auido2pose_00140-model.pth": "audio2pose",
+        "epoch_20.pth": "face_recon",
+        "facevid2vid_00189-model.pth.tar": "face-render",
+        "mapping_00109-model.pth.tar" : "mapping-109" ,
+        "mapping_00229-model.pth.tar" : "mapping-229" ,
+        "wav2lip.pth": "wav2lip",
+        "shape_predictor_68_face_landmarks.dat": "dlib",
+    }
+
+    if not os.path.isdir(current_dir):
+        return False
+    
+    dirs = os.listdir(current_dir)
+
+    for f in dirs:
+        if f in kv.keys():
+            del kv[f]
+
+    return len(kv.keys()) == 0
+
+    
+
+def download_model(local_dir='./checkpoints'):
+    REPO_ID = 'vinthony/SadTalker'
+    snapshot_download(repo_id=REPO_ID, local_dir=local_dir, local_dir_use_symlinks=False)
+
+def get_source_image(image):   
+        return image
+
+def get_img_from_txt2img(x):
+    talker_path = Path(paths.script_path) / "outputs"
+    imgs_from_txt_dir = str(talker_path / "txt2img-images/")
+    imgs = glob.glob(imgs_from_txt_dir+'/*/*.png')
+    imgs.sort(key=lambda x:os.path.getmtime(os.path.join(imgs_from_txt_dir, x)))
+    img_from_txt_path = os.path.join(imgs_from_txt_dir, imgs[-1])
+    return img_from_txt_path, img_from_txt_path
+
+def get_img_from_img2img(x):
+    talker_path = Path(paths.script_path) / "outputs"
+    imgs_from_img_dir = str(talker_path / "img2img-images/")
+    imgs = glob.glob(imgs_from_img_dir+'/*/*.png')
+    imgs.sort(key=lambda x:os.path.getmtime(os.path.join(imgs_from_img_dir, x)))
+    img_from_img_path = os.path.join(imgs_from_img_dir, imgs[-1])
+    return img_from_img_path, img_from_img_path
+ 
+def get_default_checkpoint_path():
+    # check the path of models/checkpoints and extensions/
+    checkpoint_path = Path(paths.script_path) / "models"/ "SadTalker" 
+    extension_checkpoint_path = Path(paths.script_path) / "extensions"/ "SadTalker" / "checkpoints"
+
+    if check_all_files_safetensor(checkpoint_path):
+        # print('founding sadtalker checkpoint in ' + str(checkpoint_path))
+        return checkpoint_path
+
+    if check_all_files_safetensor(extension_checkpoint_path):
+        # print('founding sadtalker checkpoint in ' + str(extension_checkpoint_path))
+        return extension_checkpoint_path
+    
+    if check_all_files(checkpoint_path):
+        # print('founding sadtalker checkpoint in ' + str(checkpoint_path))
+        return checkpoint_path
+
+    if check_all_files(extension_checkpoint_path):
+        # print('founding sadtalker checkpoint in ' + str(extension_checkpoint_path))
+        return extension_checkpoint_path
+
+    return None
+
+
+
+def install():
+
+    kv = {
+        "face_alignment": "face-alignment==1.3.5",
+        "imageio": "imageio==2.19.3",
+        "imageio_ffmpeg": "imageio-ffmpeg==0.4.7",
+        "librosa":"librosa==0.8.0",
+        "pydub":"pydub==0.25.1",
+        "scipy":"scipy==1.8.1",
+        "tqdm": "tqdm",
+        "yacs":"yacs==0.1.8",
+        "yaml": "pyyaml", 
+        "av":"av",
+        "gfpgan": "gfpgan",
+    }
+
+    # # dlib is not necessary currently
+    # if 'darwin' in sys.platform:
+    #     kv['dlib'] = "dlib"
+    # else:
+    #     kv['dlib'] = 'dlib-bin'
+
+    # #### we need to have a newer version of imageio for our method.
+    # launch.run_pip("install imageio==2.19.3", "requirements for SadTalker")
+
+    for k,v in kv.items():
+        if not launch.is_installed(k):
+            print(k, launch.is_installed(k))
+            launch.run_pip("install "+ v, "requirements for SadTalker")
+
+    if os.getenv('SADTALKER_CHECKPOINTS'):
+        print('load Sadtalker Checkpoints from '+ os.getenv('SADTALKER_CHECKPOINTS'))
+
+    elif get_default_checkpoint_path() is not None:
+        os.environ['SADTALKER_CHECKPOINTS'] = str(get_default_checkpoint_path())
+    else:
+
+        print(
+            """"
+            SadTalker will not support download all the files from hugging face, which will take a long time.
+             
+            please manually set the SADTALKER_CHECKPOINTS in `webui_user.bat`(windows) or `webui_user.sh`(linux)
+            """
+            )
+        
+        # python = sys.executable
+
+        # launch.run(f'"{python}" -m pip uninstall -y huggingface_hub', live=True)
+        # launch.run(f'"{python}" -m pip install --upgrade git+https://github.com/huggingface/huggingface_hub@main', live=True)
+        # ### run the scripts to downlod models to correct localtion.
+        # # print('download models for SadTalker')
+        # # launch.run("cd " + paths.script_path+"/extensions/SadTalker && bash ./scripts/download_models.sh", live=True)
+        # # print('SadTalker is successfully installed!')
+        # download_model(paths.script_path+'/extensions/SadTalker/checkpoints')
+    
+ 
+def on_ui_tabs():
+    install()
+
+    sys.path.extend([paths.script_path+'/extensions/SadTalker']) 
+    
+    repo_dir = paths.script_path+'/extensions/SadTalker/'
+
+    result_dir = opts.sadtalker_result_dir
+    os.makedirs(result_dir, exist_ok=True)
+
+    from app_sadtalker import sadtalker_demo  
+
+    if  os.getenv('SADTALKER_CHECKPOINTS'):
+        checkpoint_path = os.getenv('SADTALKER_CHECKPOINTS')
+    else:
+        checkpoint_path = repo_dir+'checkpoints/'
+
+    audio_to_video = sadtalker_demo(checkpoint_path=checkpoint_path, config_path=repo_dir+'src/config', warpfn = wrap_queued_call)
+   
+    return [(audio_to_video, "SadTalker", "extension")]
+
+def on_ui_settings():
+    talker_path = Path(paths.script_path) / "outputs"
+    section = ('extension', "SadTalker") 
+    opts.add_option("sadtalker_result_dir", OptionInfo(str(talker_path / "SadTalker/"), "Path to save results of sadtalker", section=section)) 
+
+script_callbacks.on_ui_settings(on_ui_settings)
+script_callbacks.on_ui_tabs(on_ui_tabs)

scripts/test.sh

@@ -0,0 +1,21 @@
+# ### some test command before commit.
+# python inference.py --preprocess crop --size 256
+# python inference.py --preprocess crop --size 512
+
+# python inference.py --preprocess extcrop --size 256
+# python inference.py --preprocess extcrop --size 512
+
+# python inference.py --preprocess resize --size 256
+# python inference.py --preprocess resize --size 512
+
+# python inference.py --preprocess full --size 256
+# python inference.py --preprocess full --size 512
+
+# python inference.py --preprocess extfull --size 256
+# python inference.py --preprocess extfull --size 512
+
+python inference.py --preprocess full --size 256 --enhancer gfpgan
+python inference.py --preprocess full --size 512 --enhancer gfpgan
+
+python inference.py --preprocess full --size 256 --enhancer gfpgan --still
+python inference.py --preprocess full --size 512 --enhancer gfpgan --still

src/gradio_demo.py

@@ -28,6 +28,7 @@ class SadTalker():
         else:
             device = "cpu"
         
+        print(f'Using device: {device}')
         self.device = device
 
         os.environ['TORCH_HOME']= checkpoint_path

webui.bat

@@ -0,0 +1,17 @@
+@echo off
+
+IF NOT EXIST venv (
+python -m venv venv
+) ELSE (
+echo venv folder already exists, skipping creation...
+)
+call .\venv\Scripts\activate.bat
+
+set PYTHON="venv\Scripts\Python.exe"
+echo venv %PYTHON%
+
+%PYTHON% App.py
+
+echo.
+echo Launch unsuccessful. Exiting.
+pause