search

YuanxunLu / LiveSpeechPortraits

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)
MIT License
1.16k stars 198 forks source link

REAL TIME 哪里去了？不是说好可以根据音频流来实时输出吗？ #96

Open 2catycm opened 6 months ago

2catycm commented 6 months ago

“To the best of our knowledge, we first present a live system that generates personalized photorealistic talking-head animation only driven by audio signals at over 30 fps. ” 这很牛啊，可是代码呢？ README里面说的demo运行的不是REAL TIME 啊？

“ Given an arbitrary input audio stream, our system generates personalized and photorealistic talking-head animation in real-time.” 可是demo.py输入的是音频文件，不是音频流啊？

而且速度也不行啊，生成一个10s的视频，需要40s

2catycm commented 6 months ago

https://github.com/YuanxunLu/LiveSpeechPortraits/issues/81 https://github.com/YuanxunLu/LiveSpeechPortraits/issues/79 https://github.com/YuanxunLu/LiveSpeechPortraits/issues/50 https://github.com/YuanxunLu/LiveSpeechPortraits/issues/41 这四个都杳无回音

2catycm commented 6 months ago

是不是实时的代码是保密的？那能给点提示吗