xtalker

xtalker copied to clipboard

How much faster than original sadtalker?

4

Hi. Thank you for your great work. How much faster than original sadtalker?

BbChip0103

AttributeError: 'NoneType' object has no attribute 'save' , i donot know why ? this is all of my issue (sadtalker) iec@iec-Default-string:~/sontung/xtalker$ python inference.py --driven_audio examples/driven_audio/bus_chinese.wav --source_image examples/source_image/art_0.png --result_dir ./result using...

SonTung2308

Trying to get my hands on Sapphire SPR CPUs, which Cloud Instance to choose from? (M7i?)

6

Hello I am trying to test this repo with the mentioned CPU, After some research I discovered that the Saphhire SPR might be called M7 ? or M7I ? ...

AIhasArrived

<parallelism number>

1

what is and expected value fpr that?

Yazdi9

Please please, can you write a script to run on Google Collab?

4

Can you? I cannot run sadtalker because it has a virus apparently. I can only run it on google collab. Could someone help me write the collab code?

AIhasArrived

( Trying to understand the README) "Install related dependencies of SadTalker" => What do you mean? Do we have to install torch==2.0.0 or torch==1.12.1+cu113,?

3

Hello I am having a hard time understanding the Readme It says "Install related dependencies of SadTalke", but it the readme from sadtalker mentions a different version of Torch, then...

AIhasArrived

Is parallelism available on GPU?

2

Can xtalker be used in multi-GPU environment? If yes, then how?

SuperMaximus1984

Have you optimized the enhancing stage?

3

I am looking for an optimized face enhancer. You have optimized the face renderer stage, that very helpful. If you achieved optimization in the enhancing stage, please reply Thank you...

shyam-kadam

AssertionError: BF16 weight prepack needs the cpu support avx512bw, avx512vl and avx512dq, please set dtype to torch.float or set weights_prepack to False.

6

Hello, I recently came across this repo, and I think it's cool. I'm interested in running SadTalker inference at much faster speeds, and I'm curious about the speedups this repo...

mayowaosibodu

deploy sadtalker with trition by cuda optimization can see here. real time.

19

[SadTalkerTriton](https://github.com/foocker/SadTalkerTriton) 25 fps , 84 frame, cost 2.4s。3090ti

foocker