import os, sys import tempfile import gradio as gr from src.gradio_demo import SadTalker from src.utils.text2speech import TTSTalker def get_source_image(image): return image def sadtalker_demo(): sad_talker = SadTalker() tts_talker = TTSTalker() with gr.Blocks(analytics_enabled=False) as sadtalker_interface: gr.Markdown("

😭 SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation (CVPR 2023)

\ Arxiv       \ Homepage       \ Github
") with gr.Row().style(equal_height=False): with gr.Column(variant='panel'): with gr.Tabs(elem_id="sadtalker_source_image"): with gr.TabItem('Upload image'): with gr.Row(): source_image = gr.Image(label="Source image", source="upload", type="filepath").style(height=256,width=256) with gr.Tabs(elem_id="sadtalker_driven_audio"): with gr.TabItem('Upload OR TTS'): with gr.Column(variant='panel'): driven_audio = gr.Audio(label="Input audio", source="upload", type="filepath") with gr.Column(variant='panel'): input_text = gr.Textbox(label="Generating audio from text", lines=5, placeholder="Alternatively, you can genreate the audio from text using @Coqui.ai TTS.") tts = gr.Button('Generate audio',elem_id="sadtalker_audio_generate", variant='primary') tts.click(fn=tts_talker.test, inputs=[input_text], outputs=[driven_audio]) with gr.Column(variant='panel'): with gr.Tabs(elem_id="sadtalker_checkbox"): with gr.TabItem('Settings'): with gr.Column(variant='panel'): is_still_mode = gr.Checkbox(label="w/ Still Mode (fewer hand motion, works on full body)") enhancer = gr.Checkbox(label="w/ 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").style(width=256) with gr.Row(): examples = [ [ 'examples/source_image/full_body_1.png', 'examples/driven_audio/bus_chinese.wav', True, False ], [ 'examples/source_image/full_body_2.png', 'examples/driven_audio/itosinger1.wav', True, False ], [ 'examples/source_image/art_13.png', 'examples/driven_audio/fayu.wav', True, False ], [ 'examples/source_image/art_5.png', 'examples/driven_audio/chinese_news.wav', True, False ], ] gr.Examples(examples=examples, inputs=[ source_image, driven_audio, is_still_mode, enhancer], outputs=[gen_video], fn=sad_talker.test, cache_examples=os.getenv('SYSTEM') == 'spaces') submit.click( fn=sad_talker.test, inputs=[source_image, driven_audio, is_still_mode, enhancer], outputs=[gen_video] ) return sadtalker_interface if __name__ == "__main__": demo = sadtalker_demo() demo.launch()