Hi @choidaedae. This is a great model! We'd love to support it but unfortunately no one on the team has the bandwidth to implement it natively. We'd be happy to review any contribution PRs and move forward with the integration.

Thanks for sharing @choidaedae and opening this to the community @a-r-r-o-w! I have just read the paper. Can I work on this model? Since you mentioned this as an integration, this will be placed in src/diffusers/pipelines/stable_virtual_camera, right; or did you talk in general, thus a community pipeline?

Hi @tolgacangoz, thanks for your attention!

I'm working with the original code and have some background with Diffusers, so happy to help with code review or sanity checks anytime. Feel free to reach out here or by email.

By the way, do you have an estimate on when the code might be ready? Just curious so I can sync up or help out if needed.

Best,
Daehyeon

Ok, I'll start coding right away. I'll ping you on the (draft) PR when needed and open it in a few days.

I started working on this model, but then I had to focus on other things, and eventually, I had to withdraw. Nevertheless, thanks for the opportunity!

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.