Age | Commit message (Collapse) | Author |
|
Translated all text on txt2img window, plus some extra
|
|
|
|
|
|
Localization WIP
|
|
|
|
update ESRGAN architecture and model to support all ESRGAN models
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Someone had 6000 images in their dataset, and it was shown as 0, which was confusing.
This will allow tracking real time dataset-average loss for registered objects.
|
|
|
|
|
|
added an option to always only show one image in previews
removed duplicate code
|
|
|
|
|
|
refer to it using that
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
[Hypernetworks] Add a feature to use dropout / more activation functions
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
getting no gradients
|
|
|
|
|
|
|
|
|
|
Implementation of CUDA device id selection (--device-id 0/1/2)
|
|
|
|
|
|
generalized some functions and option for ignoring first layer
|
|
|
|
added support for extensions
|
|
|