fq
fq
as see. i have search some resources, but it is still a problem for me at present. thx, as u say, "by assuming a billboard model where the depth is...
how to transform one to another.
batch_orth_proj(j3d_preds, cam_preds) as i understand, j3d_preds is world coords,the reason is cv2. solvePnPRansac to get world translate vec, cam_preds is the camara info of Camera space from other closed issue,...
in AvatarGen, or the weights is the same as in AvatarAnimate?(not the same) or can save it in google? model_VAE_16.pth ...
like can export to bvh? and the bvh's skeleton is ? can using in mocap?
from a video.
as the title. the main resason is, the space of /root is samll in general.
how to get more frames(3 minuts) and more fps(30-60), with only 24G GPU memory?
can here: [Bert-VITS2-Faste](https://github.com/foocker/Bert-VITS2-Faster)