ArEnSc

@yoavhacohen Just to clarify, I am trying to extend and build upon image-to-video conditioning with pose conditioning are you suggesting that we can extend the current image-to-video conditioning mechanism to...

Ok, so I believe I understand... You concatenate the pose tokens alongside the seed image tokens and noise for the remaining sequence you want to predict. keep the noise low...

@LaurentMazare you were right I fixed it! is there a way to get mimi to work on a cpu at a reasonable rate as well? I suspect this just might...

yeah I would like this to be supported on Native windows, theres a huge gap in the market that mojo can cover for AI inference, espcially in the games sector...