Added learning_rate scheduling for TI

Textual Inversion: Preprocess and Training will only pick-up image files instead

* Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS)
* Add command line option for it
* Make it default when CUDA is unavailable

Refresh list of models/ckpts upon hitting restart gradio in the setti…

add codeowners file so stop the great guys who are collaborating on the project from merging in PRs.

no pickle shall pass
thank you again, RyotaK

add features, credit for composable diffusion

rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have

Before a new batch would use the last image from the previous batch. Now
each batch will use the original image for the init image at the start of the
batch.