Integration of DC-AE (Deep Compression Autoencoder)

[DefinitlyEvil]

Is your feature request related to a problem? Please describe.
No.

Describe the solution you'd like.
As the paper stated, DCAE can achieve awesome results using lower latent dimensions.
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
https://github.com/mit-han-lab/efficientvit/blob/master/applications/dc_ae/README.md

Describe alternatives you've considered.
Using their repo directly.

Additional context.
N/A

[sayakpaul]

#9708

[DefinitlyEvil]

#9708

Cool thanks, following it rn.

[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.

[a-r-r-o-w]

Marking as closed because this has now been integrated

[DefinitlyEvil]

Awesome! <3