How to run on a single pose image?

[Exusial]

I try to run the inference on a single input pose image, but it will cause uc_mask error and cannot run.

[lixunsong]

Does single pose image mean just generate one image instead of a video?

[Exusial]

yes

[wandrzej]

just re-posing a character. and it's exactly what I was trying to do, although with 2 frame video and get the same error. I'm assuming there's some minimum length of the video that is needed and that's why get an error

[lixunsong]

We will add this pose2img pipeline, plz stay tuned :)