- 27 Nov, 2022 11 commits
-
-
AUTOMATIC1111 authored
#3449 - VRAM leak when switching to/from inpainting checkpoint
-
AUTOMATIC1111 authored
Fix setting device for GFPGAN and CodeFormer
-
AUTOMATIC1111 authored
Fixes for PyTorch 1.12.1 when using MPS
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly …
-
AUTOMATIC1111 authored
Add DPM++ SDE sampler
-
AUTOMATIC1111 authored
-
AUTOMATIC authored
-
AUTOMATIC authored
add an option to choose a different temporary directory in the UI add an option to cleanup the selected temporary directory at startup
-
- 26 Nov, 2022 7 commits
-
-
Matthew McGoogan authored
torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly set otherwise first. Updating torch_gc() to use the device set by --device-id if specified to avoid OOM edge cases on multi-GPU systems.
-
AUTOMATIC authored
-
flamelaw authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC authored
-
Jay Smith authored
-
- 23 Nov, 2022 2 commits
- 22 Nov, 2022 6 commits
- 21 Nov, 2022 2 commits
-
-
brkirch authored
Fix typo "MasOS" -> "macOS" If MPS is available and PyTorch is an earlier version than 1.13: * Monkey patch torch.Tensor.to to ensure all tensors sent to MPS are contiguous * Monkey patch torch.nn.functional.layer_norm to ensure input tensor is contiguous (required for this program to work with MPS on unmodified PyTorch 1.12.1)
-
flamelaw authored
-
- 20 Nov, 2022 5 commits
-
-
AUTOMATIC1111 authored
Enable override_settings to take effect for hypernetworks
-
AUTOMATIC authored
-
flamelaw authored
-
flamelaw authored
-
flamelaw authored
-
- 19 Nov, 2022 7 commits
-
-
AUTOMATIC authored
-
AUTOMATIC authored
-
AUTOMATIC1111 authored
Add --server-name to the list of arguments considered insecure
-
AUTOMATIC1111 authored
Fix env var name typos
-
AUTOMATIC1111 authored
feat: add http basic authentication for api
-
AUTOMATIC authored
-
Maiko Tan authored
-