SadTalker

SadTalker copied to clipboard

Face enhance速读慢，内存跑满，显卡不怎么占用

2

Face Enhancer 1分多的语音要用十几分钟，内存占用是满的，GPU占用很低，请问这个可以用GPU来跑吗？使用的是webui版的

woshixiongda

dy23

Error while decoding stream #0:0: Invalid data found when processing input [graph_0_in_0_0 @ 0000013c29347bc0] Value inf for parameter 'time_base' out of range [0 - 2.14748e+09] Last message repeated 1 times...

vtheone

File "/ML/annaconda/envs/cv/lib/python3.10/genericpath.py", line 30, in isfile st = os.stat(path) TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

2

File "/ML/annaconda/envs/cv/lib/python3.10/genericpath.py", line 30, in isfile st = os.stat(path) TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

ct1976

这是个特别牛的项目，请问SD那边能用api调用吗?

1

目前SD的速度其实还可以接受，比大部分绘画要快了。 请问如何实现在SD里API调用呢？传入图片+声音得到一个video就好，谢谢哦

baojuqiang

请问能不能通过修改BFM 的表情参数支持眨眼这样的功能？

zhaoyi10-tal

How do you change options like --pose_style & --expression_scale with webui?

2

First I want to say great job on SadTalker. Second I was wondering I noticed you have tons of extra options in inference.py, I'm running SadTalker as an extension through...

protox

作为stable-diffusion-webui的extension 使用，怎么添加 --ref_pose 的功能？ 什么时候能升级下stable-diffusion-webui的extension，已使用 --ref_pose等

newbinxxx

I run colab or hugging face but the image resolution is becoming too bad in video so how to keep the same resolution for video as in figure

besbesmany

MartinPoseidon