 AUTOMATIC
|
12c4d5c6b5
hypernetwork training mk1
|
2 年之前 |
|
AUTOMATIC
|
f7c787eb7c
make it possible to use hypernetworks without opt split attention
|
2 年之前 |
 Jairo Correa
|
ad0cc85d1f
Merge branch 'master' into stable
|
2 年之前 |
|
AUTOMATIC
|
88ec0cf557
fix for incorrect embedding token length calculation (will break seeds that use embeddings, you're welcome!)
|
2 年之前 |
|
AUTOMATIC
|
820f1dc96b
initial support for training textual inversion
|
2 年之前 |
|
Jairo Correa
|
ad1fbbae93
Merge branch 'master' into fix-vram
|
2 年之前 |
|
AUTOMATIC
|
98cc6c6e74
add embeddings dir
|
2 年之前 |
|
AUTOMATIC
|
c715ef04d1
fix for incorrect model weight loading for #814
|
2 年之前 |
|
AUTOMATIC
|
c1c27dad3b
new implementation for attention/emphasis
|
2 年之前 |
|
Jairo Correa
|
c2d5b29040
Move silu to sd_hijack
|
2 年之前 |
 Liam
|
e5707b66d6
switched the token counter to use hidden buttons instead of api call
|
2 年之前 |
|
Liam
|
5034f7d759
added token counter next to txt2img and img2img prompts
|
2 年之前 |
|
AUTOMATIC
|
073f6eac22
potential fix for embeddings no loading on AMD cards
|
2 年之前 |
 guaneec
|
615b2fc9ce
Fix token max length
|
2 年之前 |
|
AUTOMATIC
|
254da5d127
--opt-split-attention now on by default for torch.cuda, off for others (cpu and MPS; because the option does not work there according to reports)
|
2 年之前 |
|
AUTOMATIC
|
1578859305
fix for too large embeddings causing an error
|
2 年之前 |
|
AUTOMATIC
|
90401d96a6
fix a off by one error with embedding at the start of the sentence
|
2 年之前 |
|
AUTOMATIC
|
ab38392119
add the part that was missing for word textual inversion checksums
|
2 年之前 |
|
AUTOMATIC
|
cae5c5fa8d
Making opt split attention the default. Are you upset about this? Sorry.
|
2 年之前 |
 C43H66N12O12S2
|
18d6fe4346
.....
|
2 年之前 |
|
C43H66N12O12S2
|
d63dbb3acc
Move scale multiplication to the front
|
2 年之前 |
|
C43H66N12O12S2
|
72d7f8c761
fix typo
|
2 年之前 |
|
C43H66N12O12S2
|
7ec6282ec2
pass dtype to torch.zeros as well
|
2 年之前 |
|
C43H66N12O12S2
|
3b1b1444d4
Complete cross attention update
|
2 年之前 |
|
C43H66N12O12S2
|
aaea8b4494
Update cross attention to the newest version
|
2 年之前 |
|
AUTOMATIC
|
06fadd2dc5
added --opt-split-attention-v1
|
2 年之前 |
|
AUTOMATIC
|
c92f2ff196
Update to cross attention from https://github.com/Doggettx/stable-diffusion #219
|
2 年之前 |
|
AUTOMATIC
|
62ce77e245
support for sd-concepts as alternatives for textual inversion #151
|
2 年之前 |
 xeonvs
|
ba1124b326
directly convert list to tensor
|
2 年之前 |
|
xeonvs
|
65fbefd033
Added support for launching on Apple Silicon
|
2 年之前 |
