Age | Commit message (Collapse) | Author |
|
|
|
|
|
inpainting model
|
|
|
|
|
|
Save Optimizer next to TI embedding
|
|
|
|
Also add check to load only .PT and .BIN files as embeddings. (since we add .optim files in the same directory)
|
|
|
|
|
|
the new alt-diffusion model, and reformatted messages a bit #6149
|
|
|
|
|
|
|
|
|
|
Use devices.autocast() and fix MPS randn issues
|
|
Fix of the edge case 0 weight that occasionally will pop up in some specific situations. This was crashing the script.
|
|
|
|
resolve [name] after resolving [filewords] in training
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Add interrupt button to preprocessing
|
|
sampler index
|
|
|
|
|
|
Adding optional tag shuffling for training
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
set_current_image can attempt to use the VAE when it is unloaded to
the CPU while training
|
|
|
|
|
|
|
|
|
|
when unloading vae during TI training, generating images after
training will error out
|
|
https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations
|
|
option to use xattention optimizations when training
option to unload vae when training
|
|
|
|
Optimize training a little
|