One-Shot_Free-View_Neural_Talking_Head_Synthesis icon indicating copy to clipboard operation
One-Shot_Free-View_Neural_Talking_Head_Synthesis copied to clipboard

I can't download the pretrained model from baidu

Open superwhyun opened this issue 2 years ago • 7 comments

Thanks for your hard work.

However, I'm trying to download the pretrained model, but I can't because baidu does not allow accounts for non-chinese. Would you please upload the model somewhere where anybody can download?

Thanks.

p.s. To whom see this post, It is wise not to install baidu netdisk. It is almost impossible to uninstall and keeps copy itself somewhere after manual removal.

superwhyun avatar Oct 02 '21 04:10 superwhyun

I’m dealing with the same problem.

jihyeonRyu avatar Oct 06 '21 07:10 jihyeonRyu

yes, please upload to googe drive

loboere avatar Oct 06 '21 19:10 loboere

@superwhyun @jihyeonRyu @loboere Guys I have uploaded the checkpoint file to MediaFire. You should be able to download it now

zhanglonghao1992 avatar Oct 07 '21 14:10 zhanglonghao1992

Thanks a lot. I appreciate you very much.

superwhyun avatar Oct 07 '21 16:10 superwhyun

I was not able to extract the tar file downloaded from the MediaFire. It shows that "Unable to read the header". @superwhyun have you managed to extract the tar file ? Thanks

bbdamodaran avatar Nov 10 '21 11:11 bbdamodaran

@bbdamodaran Sorry fore late response. Yeah, it works well by using the file from MediaFire. However, It is compressed as a zip file, not a tar. Just change the extension of the file to 'zip', and it will work.

This is the command that I used. I hope this helps.

python demo.py --config files/vox-256.yaml --checkpoint ./files/15kp-ep119.pth.zip --source_image ./files/source.jpg --driving_video ./files/3.mp4 --relative --adapt_scale --find_best_frame --result_video ./files/result.mp4

superwhyun avatar Nov 12 '21 12:11 superwhyun

@superwhyun thanks for the details

bbdamodaran avatar Nov 12 '21 12:11 bbdamodaran