Age | Commit message (Collapse) | Author |
|
|
|
|
|
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…
|
|
project from merging in PRs.
|
|
no pickle shall pass
thank you again, RyotaK
|
|
|
|
add features, credit for composable diffusion
|
|
|
|
|
|
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.
|
|
|
|
|
|
|
|
|
|
|
|
Comma backtrack padding
|
|
|