Add VidTok AutoEncoders (#11261)
* add_autoencoder_vidtok
* format standardization
* remove small functions
* making the code style more diffusers-like
* Apply style fixes
* Add dummy objects for AutoencoderVidTok
* Fix AutoencoderVidTok avg_pool3d BFloat16 CPU compatibility
* skip test_layerwise_casting_training test
* Apply style fixes
---------
Co-authored-by: annitang1997 <memory97@sjtu.edu.cn>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
