Paella v3

[patrickvonplaten]

Model/Pipeline/Scheduler description

Moving outdated pull request: #2058 here.

The amazing @dome272 published a new paella model which is significantly more performant than the previous models while being very fast.

https://laion.ai/blog/paella/

I think it would be a very nice addition to the library given it's superior speed.

Anybody interested in picking this one up?

Open source status

• The model implementation is available
• The model weights are available (Only relevant if addition is not a scheduler).

Provide useful links for the implementation

https://laion.ai/blog/paella/

Paper: https://arxiv.org/abs/2211.07292
Code: https://github.com/dome272/Paella
Model: https://huggingface.co/dome272/Paella

@dome272

[dome272]

Quick addon to the first sentence. @pabloppp is the true brain behind paella who came up with many many cool ideas and keeps flashing me with new ideas every day. So much much credit to him!

[patrickvonplaten]

Sorry to forget you here @pabloppp 😅

[github-actions]

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.

[patrickvonplaten]

This is still not added yet I believe

[github-actions]

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.