AUTOMATIC
|
ce6911158b
|
Add support Stable Diffusion 2.0
|
3 years ago |
|
AUTOMATIC
|
cdc8020d13
|
change StableDiffusionProcessing to internally use sampler name instead of sampler index
|
3 years ago |
|
AUTOMATIC
|
159475e072
|
tweak names a bit for new samplers
|
3 years ago |
hentailord85ez
|
1b6c2fc749
|
Reorder samplers
|
3 years ago |
|
hentailord85ez
|
f92dc505a0
|
Fix name
|
3 years ago |
|
hentailord85ez
|
6008c0773e
|
Add support for new DPM-Solver++ samplers
|
3 years ago |
|
AUTOMATIC
|
eb5e82c7dd
|
do not unnecessarily run VAE one more time when saving intermediate image with hires fix
|
3 years ago |
timntorres
|
9c67408004
|
Allow saving "before-highres-fix. (#4150)
* Save image/s before doing highres fix.
|
3 years ago |
|
AUTOMATIC1111
|
10f62546d3
|
Merge pull request #4021 from AUTOMATIC1111/add-kdiff-cfgdenoiser-callback
Add mid-kdiffusion cfgdenoiser script callback - access latents, conditionings and sigmas mid-sampling
|
3 years ago |
DepFA
|
5b6bedf6f2
|
Update class name and assign back to vars
|
3 years ago |
|
DepFA
|
8ae0ea9dea
|
Add callback to sd_samplers
|
3 years ago |
Martin Cairns
|
34c86c12b0
|
Include PLMS in adjust steps as it also can fail in the same way
|
3 years ago |
|
Martin Cairns
|
de1dc0d279
|
Add adjust_steps_if_invalid to find next valid step for ddim uniform sampler
|
3 years ago |
ritosonn
|
b383702752
|
fix #3145 #3093
|
3 years ago |
|
AUTOMATIC
|
d213d6ca6f
|
removed the option to use 2x more memory when generating previews
added an option to always only show one image in previews
removed duplicate code
|
3 years ago |
Unnoen
|
4fdb53c1e9
|
Generate grid preview for progress image
|
3 years ago |
|
AUTOMATIC1111
|
d6bd6a425d
|
Merge branch 'master' into master
|
3 years ago |
Vladimir Repin
|
d23a46ceaa
|
Different approach to skip/interrupt with highres fix
|
3 years ago |
random_thoughtss
|
92a17a7a4a
|
Made dummy latents smaller. Minor code cleanups
|
3 years ago |
|
random_thoughtss
|
c418467c03
|
Don't compute latent mask if were not using it. Also added support for fixed highres_fix generation.
|
3 years ago |
|
random_thoughtss
|
dde9f96072
|
added support for ddim img2img
|
3 years ago |
|
random_thoughtss
|
8e7097d06a
|
Added support for RunwayML inpainting model
|
3 years ago |
|
AUTOMATIC
|
cbf15edbf9
|
remove dependence on TQDM for sampler progress/interrupt functionality
|
3 years ago |
Martin Cairns
|
eacc03b167
|
Fix typo in comments
|
3 years ago |
|
Martin Cairns
|
1eae307607
|
Remove debug code for checking that first sigma value is same after code cleanup
|
3 years ago |
|
Martin Cairns
|
92d7a13885
|
Handle different parameters for DPM fast & adaptive
|
3 years ago |
|
AUTOMATIC
|
7349088d32
|
--no-half-vae
|
3 years ago |
Aidan Holland
|
432782163a
|
chore: Fix typos
|
3 years ago |
|
AUTOMATIC
|
77f4237d1c
|
fix bugs related to variable prompt lengths
|
3 years ago |
Trung Ngo
|
00117a07ef
|
check specifically for skipped
|
3 years ago |
|
AUTOMATIC
|
b34b25b4c9
|
karras samplers for img2img?
|
3 years ago |
|
AUTOMATIC
|
5993df24a1
|
integrate the new samplers PR
|
3 years ago |
C43H66N12O12S2
|
71901b3d3b
|
add karras scheduling variants
|
3 years ago |
|
AUTOMATIC
|
5f24b7bcf4
|
option to let users select which samplers they want to hide
|
3 years ago |
|
AUTOMATIC
|
c26732fbee
|
added support for AND from https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
|
3 years ago |
|
hentailord85ez
|
34c638142e
|
Fixed when eta = 0
Unexpected behavior when using eta = 0 in something like XY, but your default eta was set to something not 0.
|
3 years ago |
|
AUTOMATIC
|
3ff0de2c59
|
added --disable-console-progressbars to disable progressbars in console
disabled printing prompts to console by default, enabled by --enable-console-prompts
|
3 years ago |
|
DepFA
|
bc38c80cfc
|
add sampler_noise_scheduler_override switch
|
3 years ago |
|
AUTOMATIC
|
f80c3696f6
|
fix the sys not found error when importing sd_samplers that appeared after PR
|
3 years ago |
|
C43H66N12O12S2
|
28307a9f10
|
force usage of cloned k-diffusion
|
3 years ago |
|
C43H66N12O12S2
|
965dcf4469
|
improve code quality
|
3 years ago |
|
C43H66N12O12S2
|
b05355770c
|
add new samplers
|
3 years ago |
|
AUTOMATIC
|
d62954c2bc
|
fix broken DDIM with img2img
|
3 years ago |
|
AUTOMATIC
|
d64b451681
|
added support for automatically installing latest k-diffusion
added eta parameter to parameters output for generated images
split eta settings into ancestral and ddim (because they have different default values)
|
3 years ago |
|
AUTOMATIC
|
2ab64ec81a
|
emergency fix for #1199
|
3 years ago |
|
C43H66N12O12S2
|
8644e494be
|
add eta to k ancestral
|
3 years ago |
|
DepFA
|
adbd26a68f
|
add missing s_tmax
|
3 years ago |
|
DepFA
|
48d5796f0d
|
pass eta to tex2img sampler
|
3 years ago |
|
DepFA
|
a860839f1f
|
take extra sampler properties from StableDiffusionProcessing
|
3 years ago |
|
DepFA
|
2ab3d593f9
|
pass extra KDiffusionSampler function parameters
|
3 years ago |