Age | Commit message (Collapse) | Author |
|
|
|
fix model override logic
|
|
Improve interrupt speed
|
|
|
|
|
|
do not need extra logic to unload refine model
|
|
|
|
many prompts/negative prompts there are #12509
|
|
rather than in settings
|
|
|
|
|
|
|
|
|
|
add new callback for scripts to be used before processing
|
|
Clear sampler and garbage collect before decoding images to reduce VRAM
|
|
logging for error output in console
|
|
More significant VRAM reduction.
|
|
|
|
write out correct model name in infotext, rather than the refiner model
|
|
|
|
add VAE from main model into infotext, not from refiner model
option to make scripts UI without gr.Group
fix inconsistencies with refiner when usings samplers that do more denoising than steps
|
|
|
|
Make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur`
|
|
|
|
|
|
|
|
setting if you want them back
|
|
rework hires fix UI to use accordion
prevent bogus progress output in console when calculating hires fix dimensions
|
|
|
|
|
|
of multiplie images
|
|
fix typo
|
|
is greater than 1
|
|
|
|
|
|
|
|
add proper support for recalculating conds in k-diffusion samplers
remove support for compvis samplers
|
|
|
|
|
|
|
|
|
|
|
|
|
|
don't save incomplete images
|
|
|
|
|
|
|
|
|
|
|
|
|