Age | Commit message (Collapse) | Author |
|
|
|
|
|
* 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…
|
|
no pickle shall pass
thank you again, RyotaK
|
|
|
|
|
|
filename that people who use zip instead of git clone will have
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Comma backtrack padding
|
|
|
|
|
|
|
|
|
|
|
|
Add VAE Path Arguments
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Unlimited tokens actually work now. Works with textual inversion too. Replaces the previous not-so-much-working implementation.
|
|
|
|
|
|
|
|
per input image in a single epoch
|
|
|
|
|
|
Pytorch 1.13 and later will rename _TypedStorage to TypedStorage, so check for TypedStorage and use _TypedStorage if it is not available. Currently this is needed so that nightly builds of PyTorch work correctly.
|
|
https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master
|
|
|
|
|
|
|
|
|
|
|
|
|
|
possible
|