[REQ] Will LCM model training?

I don't know if it's possible to train LCM models or convert an existing model to LCM, but it would be good for users with weak machines.
A description of the LCM model is here:
https://arxiv.org/abs/2310.04378

Their website:
https://latent-consistency-models.github.io/

And here:
https://github.com/luosiallen/latent-consistency-model

The Fast Stable Diffusion app page:
https://github.com/rupeshs/fastsdcpu

No repository files, tests, or entry points are named. Start by reading the linked LCM paper and reference implementation, then compare their training or conversion requirements with this repository. Done would require a defined, tested way to train or convert LCM models, but the issue does not specify the intended scope.

Written by the indexing model from the issue text.