Spaces:
Paused
Paused
File size: 4,521 Bytes
cff9535 416263d cff9535 416263d cff9535 416263d cff9535 416263d cff9535 416263d 2299694 416263d cff9535 416263d cff9535 416263d cff9535 416263d cff9535 9beb764 416263d 9beb764 a86a2b8 416263d cff9535 416263d cff9535 a86a2b8 416263d a86a2b8 416263d a86a2b8 416263d a86a2b8 416263d cff9535 416263d cff9535 416263d cff9535 a22eb82 cff9535 a22eb82 416263d 9801f4f a22eb82 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
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("<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> \
<a style='font-size:18px;color: #efefef' href='https://sadtalker.github.io'>Homepage</a> \
<a style='font-size:18px;color: #efefef' href='https://github.com/Winfredy/SadTalker'> Github </div>")
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()
|