aboutsummaryrefslogtreecommitdiffstats
path: root/modules/sd_samplers.py
AgeCommit message (Collapse)AuthorLines
2023-08-08pass samplers from UI by name, make it possible to use a sampler from ↵AUTOMATIC1111-4/+9
infotext even if it's hidden in the dropdown
2023-08-08REMOVEAUTOMATIC1111-5/+2
2023-08-08add CFG denoiser implementation for DDIM, PLMS and UniPC (this is the commit ↵AUTOMATIC1111-1/+2
when you can run both old and new implementations to compare them)
2023-07-14add a message about unsupported samplersAUTOMATIC1111-0/+3
2023-05-16suppress ENSD infotext for samplers that don't use itAUTOMATIC-1/+7
2023-05-10F401 fixes for ruffAUTOMATIC-1/+1
2023-02-10UniPC does not support img2img (for now)space-nuko-1/+1
2023-01-30split samplers into one more files for k-diffusionAUTOMATIC-297/+5
2023-01-30Split history sd_samplers.py to sd_samplers_kdiffusion.pyAndrey-0/+339
2023-01-30Split history sd_samplers.py to sd_samplers_kdiffusion.pyAndrey-339/+0
2023-01-30split compvis sampler and shared sampler stuff into their own filesAUTOMATIC-228/+15
2023-01-30Split history sd_samplers.py to sd_samplers_common.pyAndrey-0/+552
2023-01-30Split history sd_samplers.py to sd_samplers_common.pyAndrey-552/+0
2023-01-30Split history sd_samplers.py to sd_samplers_compvis.pyAndrey-0/+552
2023-01-30Split history sd_samplers.py to sd_samplers_compvis.pyAndrey-552/+0
2023-01-25fix prompt editing break after first batch in img2imgAUTOMATIC-1/+1
2023-01-16Add a check and explanation for tensor with all NaNs.AUTOMATIC-0/+2
2023-01-15big rework of progressbar/preview system to allow multiple users to prompts ↵AUTOMATIC-1/+1
at the same time and do not get previews of each other
2023-01-14add an option to choose what you want to see in live preview (Live preview ↵AUTOMATIC-5/+10
subject) and moves live preview settings to its own tab
2023-01-05add Discard penultimate sigma to infotextAUTOMATIC-3/+7
2023-01-05Merge pull request #6044 from hentailord85ez/discard-penultimate-sigmaAUTOMATIC1111-1/+4
Allow always discarding of penultimate sigma and fix doing 1 less step than specified
2023-01-04fix incorrect display/calculation for number of steps for hires fix in ↵AUTOMATIC-2/+3
progress bars
2023-01-01change karras scheduler sigmas to values recommended by SD from old 0.1 to ↵AUTOMATIC-1/+3
10 with an option to revert to old
2022-12-26Update sd_samplers.pyhentailord85ez-1/+4
2022-12-24added cheap NN approximation for VAEAUTOMATIC-13/+16
2022-12-24Merge pull request #5976 from AbstractQbit/fast_previewAUTOMATIC1111-7/+16
Add an option for faster low quality previews
2022-12-24separate part of denoiser code into a function to make it easier for ↵AUTOMATIC-6/+11
extensions to override it
2022-12-24Add an option for faster low quality previewsAbstractQbit-7/+16
2022-12-24eliminate duplicated codeAUTOMATIC-17/+14
add an option to samplers for skipping next to last sigma
2022-12-18fix dpm2 in img2img as wellAlex "mcmonkey" Goodwin-0/+3
2022-12-16apply to DPM2 (non-ancestral) as wellAlex "mcmonkey" Goodwin-1/+1
2022-12-16Add a workaround patch for DPM2 a issueAlex "mcmonkey" Goodwin-0/+3
DPM2 a and DPM2 a Karras samplers are both affected by an issue described by https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3483 and can be resolved by a workaround suggested by the k-diffusion author at https://github.com/crowsonkb/k-diffusion/issues/43#issuecomment-1305195666
2022-11-30Rework MPS randn fix, add randn_like fixbrkirch-3/+5
torch.manual_seed() already sets a CPU generator, so there is no reason to create a CPU generator manually. torch.randn_like also needs a MPS fix for k-diffusion, but a torch hijack with randn_like already exists so it can also be used for that.
2022-11-30Add workaround for using MPS with torchsdebrkirch-0/+14
2022-11-27rework #5012 to also work for pictures dragged into the prompt and also add ↵AUTOMATIC-1/+1
Clip skip + ENSD to parameters
2022-11-27Merge pull request #5065 from JaySmithWpg/vram-leakAUTOMATIC1111-18/+15
#3449 - VRAM leak when switching to/from inpainting checkpoint
2022-11-27calculate dictionary for sampler names only onceAUTOMATIC-0/+7
2022-11-27Merge branch 'master' into DPM++SDEAUTOMATIC1111-6/+8
2022-11-26Add support Stable Diffusion 2.0AUTOMATIC-6/+8
2022-11-25fixes #3449 - VRAM leak when switching to/from inpainting modelJay Smith-18/+15
2022-11-22Add DPM++ SDE sampleruservar-0/+2
2022-11-19change StableDiffusionProcessing to internally use sampler name instead of ↵AUTOMATIC-3/+10
sampler index
2022-11-05tweak names a bit for new samplersAUTOMATIC-4/+4
2022-11-04Reorder samplershentailord85ez-2/+2
2022-11-04Fix namehentailord85ez-1/+1
2022-11-04Add support for new DPM-Solver++ samplershentailord85ez-0/+4
2022-11-02do not unnecessarily run VAE one more time when saving intermediate image ↵AUTOMATIC-0/+1
with hires fix
2022-11-02Allow saving "before-highres-fix. (#4150)timntorres-3/+2
* Save image/s before doing highres fix.
2022-11-02Merge pull request #4021 from AUTOMATIC1111/add-kdiff-cfgdenoiser-callbackAUTOMATIC1111-0/+7
Add mid-kdiffusion cfgdenoiser script callback - access latents, conditionings and sigmas mid-sampling
2022-11-02Update class name and assign back to varsDepFA-2/+6