index
:
stable-diffusion-webui-gfx803.git
master
stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
modules
/
sd_hijack.py
Age
Commit message (
Collapse
)
Author
2022-10-02
Merge branch 'master' into stable
Jairo Correa
2022-10-02
fix for incorrect embedding token length calculation (will break seeds that ↵
AUTOMATIC
use embeddings, you're welcome!) add option to input initialization text for embeddings
2022-10-02
initial support for training textual inversion
AUTOMATIC
2022-09-30
Merge branch 'master' into fix-vram
Jairo Correa
2022-09-30
add embeddings dir
AUTOMATIC
2022-09-29
fix for incorrect model weight loading for #814
AUTOMATIC
2022-09-29
new implementation for attention/emphasis
AUTOMATIC
2022-09-29
Move silu to sd_hijack
Jairo Correa
2022-09-27
switched the token counter to use hidden buttons instead of api call
Liam
2022-09-27
added token counter next to txt2img and img2img prompts
Liam
2022-09-25
potential fix for embeddings no loading on AMD cards
AUTOMATIC
2022-09-25
Fix token max length
guaneec
2022-09-21
--opt-split-attention now on by default for torch.cuda, off for others (cpu ↵
AUTOMATIC
and MPS; because the option does not work there according to reports)
2022-09-21
fix for too large embeddings causing an error
AUTOMATIC
2022-09-20
fix a off by one error with embedding at the start of the sentence
AUTOMATIC
2022-09-20
add the part that was missing for word textual inversion checksums
AUTOMATIC
2022-09-18
Making opt split attention the default. Are you upset about this? Sorry.
AUTOMATIC
2022-09-18
.....
C43H66N12O12S2
2022-09-18
Move scale multiplication to the front
C43H66N12O12S2
2022-09-15
fix typo
C43H66N12O12S2
2022-09-15
pass dtype to torch.zeros as well
C43H66N12O12S2
2022-09-13
Complete cross attention update
C43H66N12O12S2
2022-09-12
Update cross attention to the newest version
C43H66N12O12S2
2022-09-11
added --opt-split-attention-v1
AUTOMATIC
2022-09-10
Update to cross attention from https://github.com/Doggettx/stable-diffusion #219
AUTOMATIC
2022-09-08
support for sd-concepts as alternatives for textual inversion #151
AUTOMATIC
2022-09-07
directly convert list to tensor
xeonvs
2022-09-07
Added support for launching on Apple Silicon
xeonvs
2022-09-05
re-integrated tiling option as a UI element
AUTOMATIC
2022-09-05
add an option to enable tiling image generation
AUTOMATIC
2022-09-05
add split attention layer optimization from ↵
AUTOMATIC
https://github.com/basujindal/stable-diffusion/pull/117
2022-09-03
split codebase into multiple files; to anyone this affects negatively: sorry
AUTOMATIC