 AUTOMATIC1111
|
0769aa318a
integrated edits as recommended in the PR #15804
|
hai 1 ano |
 huchenlei
|
0e98529365
Replace einops.rearrange with torch native
|
hai 1 ano |
 brkirch
|
87dd685224
Make sub-quadratic the default for MPS
|
%!s(int64=2) %!d(string=hai) anos |
|
brkirch
|
abfa4ad8bc
Use fixed size for sub-quadratic chunking on MPS
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC1111
|
10ff071e33
update doggettx cross attention optimization to not use an unreasonable amount of memory in some edge cases -- suggestion by MorkTheOrk
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC1111
|
ac4ccfa136
get attention optimizations to work
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC1111
|
da464a3fb3
SDXL support
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC1111
|
806ea639e6
Merge pull request #11066 from aljungberg/patch-1
|
%!s(int64=2) %!d(string=hai) anos |
 Alexander Ljungberg
|
d9cc0910c8
Fix upcast attention dtype error.
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC1111
|
56bf522913
Merge pull request #10990 from vkage/sd_hijack_optimizations_bugfix
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
2e23c9c568
fix the broken line for #10990
|
%!s(int64=2) %!d(string=hai) anos |
 Vivek K. Vasishtha
|
b1a72bc7e2
torch.cuda.is_available() check for SdOptimizationXformers
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
3ee1238630
revert default cross attention optimization to Doggettx
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
36888092af
revert default cross attention optimization to Doggettx
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
05933840f0
rename print_error to report, use it with together with package name
|
%!s(int64=2) %!d(string=hai) anos |
 Aarni Koskela
|
00dfe27f59
Add & use modules.errors.print_error where currently printing exception info by hand
|
%!s(int64=2) %!d(string=hai) anos |
|
Aarni Koskela
|
df004be2fc
Add a couple `from __future__ import annotations`es for Py3.9 compat
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC1111
|
1e5afd4fa9
Apply suggestions from code review
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
8a3d232839
fix linter issues
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
2582a0fd3b
make it possible for scripts to add cross attention optimizations
|
%!s(int64=2) %!d(string=hai) anos |
|
Aarni Koskela
|
49a55b410b
Autofix Ruff W (not W605) (mostly whitespace)
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
028d3f6425
ruff auto fixes
|
%!s(int64=2) %!d(string=hai) anos |
|
AUTOMATIC
|
762265eab5
autofixes from ruff
|
%!s(int64=2) %!d(string=hai) anos |
|
brkirch
|
7aab389d6f
Fix for Unet NaNs
|
%!s(int64=2) %!d(string=hai) anos |
 FNSpd
|
280ed8f00f
Update sd_hijack_optimizations.py
|
%!s(int64=2) %!d(string=hai) anos |
|
FNSpd
|
c84c9df737
Update sd_hijack_optimizations.py
|
%!s(int64=2) %!d(string=hai) anos |
 Pam
|
8d7fa2f67c
sdp_attnblock_forward hijack
|
%!s(int64=2) %!d(string=hai) anos |
|
Pam
|
37acba2633
argument to disable memory efficient for sdp
|
%!s(int64=2) %!d(string=hai) anos |
|
Pam
|
fec0a89511
scaled dot product attention
|
%!s(int64=2) %!d(string=hai) anos |
|
brkirch
|
e3b53fd295
Add UI setting for upcasting attention to float32
|
%!s(int64=2) %!d(string=hai) anos |
