- 14 Dec, 2023 12 commits
-
-
AUTOMATIC1111 authored
add option: Live preview in full page image viewer
-
AUTOMATIC1111 authored
Soft Inpainting
-
AUTOMATIC1111 authored
[IPEX] Fix embedding and ControlNet
-
AUTOMATIC1111 authored
Re-add setting lost as part of e294e46d
-
AUTOMATIC1111 authored
Fix styles
-
AUTOMATIC1111 authored
Assign id for "extra_options". Replace numeric field with slider.
-
AUTOMATIC1111 authored
Allow pasting in WIDTHxHEIGHT strings into the width/height fields
-
AUTOMATIC1111 authored
Fix wrong implementation in network_oft
-
Kohaku-Blueleaf authored
-
Kohaku-Blueleaf authored
-
Kohaku-Blueleaf authored
-
Kohaku-Blueleaf authored
-
- 13 Dec, 2023 1 commit
-
-
Aarni Koskela authored
-
- 10 Dec, 2023 4 commits
- 09 Dec, 2023 5 commits
-
-
kaalibro authored
-
Nuullll authored
-
Nuullll authored
-
CodeHatchling authored
-
CodeHatchling authored
soft_inpainting now appears in the "inpaint" section, and will not activate unless inpainting is activated.
-
- 08 Dec, 2023 7 commits
-
-
CodeHatchling authored
-
CodeHatchling authored
-
CodeHatchling authored
-
CodeHatchling authored
-
CodeHatchling authored
-
CodeHatchling authored
-
CodeHatchling authored
Re-implemented soft inpainting via a script. Also fixed some mistakes with the previous hooks, removed unnecessary formatting changes, removed code that I had forgotten to.
-
- 07 Dec, 2023 3 commits
-
-
CodeHatchling authored
-
CodeHatchling authored
Removed changes in some scripts since the arguments for soft painting are no longer passed through the same path as "mask_blur".
-
CodeHatchling authored
-
- 06 Dec, 2023 2 commits
-
-
w-e-w authored
make #13459 "show the preview image in the modal view if available" optional
-
Nuullll authored
Cast `torch.bmm` args into same `dtype`. Fixes the following error when using Text Inversion embedding (#14224): ``` RuntimeError: could not create a primitive descriptor for a matmul primitive ```
-
- 05 Dec, 2023 6 commits
-
-
AUTOMATIC1111 authored
remove clean_text()
-
CodeHatchling authored
# Conflicts: # modules/processing.py
-
CodeHatchling authored
-
CodeHatchling authored
Fixed issue where batched inpainting (batch size > 1) wouldn't work because of mismatched tensor sizes. The 'already_decoded' decoded case should also be handled correctly (tested indirectly).
-
CodeHatchling authored
-
CodeHatchling authored
-