- 25 Jan, 2023 2 commits
-
-
brkirch authored
Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers. In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also.
-
brkirch authored
This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half().
-
- 24 Jan, 2023 14 commits
-
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC authored
add PIP_INSTALLER_LOCATION env var to install pip if it's not installed remove accidental call to accelerate when venv is disabled add another env var to skip venv - SKIP_VENV
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC authored
also return the removed field to sdapi/v1/upscalers because someone might have relied on it existing
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
Add exception handling to API image decode
-
AUTOMATIC1111 authored
Make SwinIR upscaler interruptible and skippable
-
AUTOMATIC1111 authored
Set Linux xformers 0.0.16RC425
-
acncagua authored
-
catboxanon authored
-
catboxanon authored
-
- 23 Jan, 2023 24 commits
-
-
Vladimir Mandic authored
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
Add selector to interrogate categories
-
AUTOMATIC authored
-
AUTOMATIC authored
you can all now stop worrying about it
-
Vladimir Mandic authored
-
Vladimir Mandic authored
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
Extra network view style
-
AUTOMATIC1111 authored
API should use same image format as specified in WebUI settings
-
Guillermo Moreno authored
-
AUTOMATIC authored
-
Vladimir Mandic authored
-
AUTOMATIC authored
-
AUTOMATIC authored
add a message about new torch/xformers version and a way to upgrade by specifying a commandline flag
-
AUTOMATIC1111 authored
upgrading torch, torchvision, xformers (windows), to use cu117
-
Vladimir Mandic authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
Adds Hires Steps to X/Y Plot, and updates step calculation
-
AUTOMATIC1111 authored
Fixes various button overflowing UI and compact checkbox
-
AUTOMATIC1111 authored
Fix dark mode
-
AUTOMATIC authored
-