Wang Qiang

 I found that it seems to only support Python versions 3.8 and above. After updating the Python version, the installation can be completed smoothly

https://pypi.org/project/motion-vector-extractor/#files

> > > The two folders (part1 and part2) you can access by the above link contain all the shapenet training data now :) Good works! thanks for you contribution!

https://github.com/wangqiang9/Finetune-SVD

I am trying to train it: https://github.com/wangqiang9/Finetune-SVD/

I think the completed task has some similarities with “DreamPose: Fashion Image to Video Synthesis via Stable Diffusion”, but the latter is also not open-source.

https://github.com/xieqk/Bilibili_Spider_by_UserID/pull/7

> Hi. I will release the training code this month. Currently, I am too busy with other research projects. Thanks for your interest and patience. Thank you. Looking forward to...

Hi, when you using the different single dataset, the pen break needs to be reset, otherwise it will result in discontinuous strokes.

Also, does your result look like apple? It seems that the shape information model has learned some and needs to adjust the pen break parameters again.