| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Add a check and explanation for tensor with all NaNs. | AUTOMATIC | 2023-01-16 | 1 | -0/+2 |
| | | |||||
| * | big rework of progressbar/preview system to allow multiple users to prompts ↵ | AUTOMATIC | 2023-01-15 | 1 | -1/+1 |
| | | | | | at the same time and do not get previews of each other | ||||
| * | add an option to choose what you want to see in live preview (Live preview ↵ | AUTOMATIC | 2023-01-14 | 1 | -5/+10 |
| | | | | | subject) and moves live preview settings to its own tab | ||||
| * | add Discard penultimate sigma to infotext | AUTOMATIC | 2023-01-05 | 1 | -3/+7 |
| | | |||||
| * | Merge pull request #6044 from hentailord85ez/discard-penultimate-sigma | AUTOMATIC1111 | 2023-01-05 | 1 | -1/+4 |
| |\ | | | | | Allow always discarding of penultimate sigma and fix doing 1 less step than specified | ||||
| | * | Update sd_samplers.py | hentailord85ez | 2022-12-26 | 1 | -1/+4 |
| | | | |||||
| * | | fix incorrect display/calculation for number of steps for hires fix in ↵ | AUTOMATIC | 2023-01-04 | 1 | -2/+3 |
| | | | | | | | | | progress bars | ||||
| * | | change karras scheduler sigmas to values recommended by SD from old 0.1 to ↵ | AUTOMATIC | 2023-01-01 | 1 | -1/+3 |
| |/ | | | | 10 with an option to revert to old | ||||
| * | added cheap NN approximation for VAE | AUTOMATIC | 2022-12-24 | 1 | -13/+16 |
| | | |||||
| * | Merge pull request #5976 from AbstractQbit/fast_preview | AUTOMATIC1111 | 2022-12-24 | 1 | -7/+16 |
| |\ | | | | | Add an option for faster low quality previews | ||||
| | * | Add an option for faster low quality previews | AbstractQbit | 2022-12-24 | 1 | -7/+16 |
| | | | |||||
| * | | separate part of denoiser code into a function to make it easier for ↵ | AUTOMATIC | 2022-12-24 | 1 | -6/+11 |
| |/ | | | | extensions to override it | ||||
| * | eliminate duplicated code | AUTOMATIC | 2022-12-24 | 1 | -17/+14 |
| | | | | | add an option to samplers for skipping next to last sigma | ||||
| * | fix dpm2 in img2img as well | Alex "mcmonkey" Goodwin | 2022-12-19 | 1 | -0/+3 |
| | | |||||
| * | apply to DPM2 (non-ancestral) as well | Alex "mcmonkey" Goodwin | 2022-12-16 | 1 | -1/+1 |
| | | |||||
| * | Add a workaround patch for DPM2 a issue | Alex "mcmonkey" Goodwin | 2022-12-16 | 1 | -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 | ||||
| * | Rework MPS randn fix, add randn_like fix | brkirch | 2022-11-30 | 1 | -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. | ||||
| * | Add workaround for using MPS with torchsde | brkirch | 2022-11-30 | 1 | -0/+14 |
| | | |||||
| * | rework #5012 to also work for pictures dragged into the prompt and also add ↵ | AUTOMATIC | 2022-11-27 | 1 | -1/+1 |
| | | | | | Clip skip + ENSD to parameters | ||||
| * | Merge pull request #5065 from JaySmithWpg/vram-leak | AUTOMATIC1111 | 2022-11-27 | 1 | -18/+15 |
| |\ | | | | | #3449 - VRAM leak when switching to/from inpainting checkpoint | ||||
| | * | fixes #3449 - VRAM leak when switching to/from inpainting model | Jay Smith | 2022-11-26 | 1 | -18/+15 |
| | | | |||||
| * | | calculate dictionary for sampler names only once | AUTOMATIC | 2022-11-27 | 1 | -0/+7 |
| | | | |||||
| * | | Merge branch 'master' into DPM++SDE | AUTOMATIC1111 | 2022-11-27 | 1 | -6/+8 |
| |\ \ | |||||
| | * | | Add support Stable Diffusion 2.0 | AUTOMATIC | 2022-11-26 | 1 | -6/+8 |
| | |/ | |||||
| * / | Add DPM++ SDE sampler | uservar | 2022-11-22 | 1 | -0/+2 |
| |/ | |||||
| * | change StableDiffusionProcessing to internally use sampler name instead of ↵ | AUTOMATIC | 2022-11-19 | 1 | -3/+10 |
| | | | | | sampler index | ||||
| * | tweak names a bit for new samplers | AUTOMATIC | 2022-11-05 | 1 | -4/+4 |
| | | |||||
| * | Reorder samplers | hentailord85ez | 2022-11-04 | 1 | -2/+2 |
| | | |||||
| * | Fix name | hentailord85ez | 2022-11-04 | 1 | -1/+1 |
| | | |||||
| * | Add support for new DPM-Solver++ samplers | hentailord85ez | 2022-11-04 | 1 | -0/+4 |
| | | |||||
| * | do not unnecessarily run VAE one more time when saving intermediate image ↵ | AUTOMATIC | 2022-11-02 | 1 | -0/+1 |
| | | | | | with hires fix | ||||
| * | Allow saving "before-highres-fix. (#4150) | timntorres | 2022-11-02 | 1 | -3/+2 |
| | | | | * Save image/s before doing highres fix. | ||||
| * | Merge pull request #4021 from AUTOMATIC1111/add-kdiff-cfgdenoiser-callback | AUTOMATIC1111 | 2022-11-02 | 1 | -0/+7 |
| |\ | | | | | Add mid-kdiffusion cfgdenoiser script callback - access latents, conditionings and sigmas mid-sampling | ||||
| | * | Update class name and assign back to vars | DepFA | 2022-11-02 | 1 | -2/+6 |
| | | | |||||
| | * | Add callback to sd_samplers | DepFA | 2022-10-30 | 1 | -0/+3 |
| | | | |||||
| * | | Include PLMS in adjust steps as it also can fail in the same way | Martin Cairns | 2022-10-30 | 1 | -1/+1 |
| | | | |||||
| * | | Add adjust_steps_if_invalid to find next valid step for ddim uniform sampler | Martin Cairns | 2022-10-29 | 1 | -13/+15 |
| |/ | |||||
| * | fix #3145 #3093 | ritosonn | 2022-10-25 | 1 | -2/+2 |
| | | |||||
| * | removed the option to use 2x more memory when generating previews | AUTOMATIC | 2022-10-22 | 1 | -25/+10 |
| | | | | | | added an option to always only show one image in previews removed duplicate code | ||||
| * | Generate grid preview for progress image | Unnoen | 2022-10-22 | 1 | -1/+25 |
| | | |||||
| * | Merge branch 'master' into master | AUTOMATIC1111 | 2022-10-21 | 1 | -11/+49 |
| |\ | |||||
| | * | Made dummy latents smaller. Minor code cleanups | random_thoughtss | 2022-10-20 | 1 | -2/+4 |
| | | | |||||
| | * | Don't compute latent mask if were not using it. Also added support for fixed ↵ | random_thoughtss | 2022-10-19 | 1 | -0/+4 |
| | | | | | | | | | highres_fix generation. | ||||
| | * | added support for ddim img2img | random_thoughtss | 2022-10-19 | 1 | -0/+6 |
| | | | |||||
| | * | Added support for RunwayML inpainting model | random_thoughtss | 2022-10-19 | 1 | -12/+38 |
| | | | |||||
| * | | Different approach to skip/interrupt with highres fix | Vladimir Repin | 2022-10-20 | 1 | -0/+4 |
| |/ | |||||
| * | remove dependence on TQDM for sampler progress/interrupt functionality | AUTOMATIC | 2022-10-18 | 1 | -49/+58 |
| | | |||||
| * | Fix typo in comments | Martin Cairns | 2022-10-11 | 1 | -1/+1 |
| | | |||||
| * | Remove debug code for checking that first sigma value is same after code cleanup | Martin Cairns | 2022-10-11 | 1 | -1/+0 |
| | | |||||
| * | Handle different parameters for DPM fast & adaptive | Martin Cairns | 2022-10-11 | 1 | -7/+18 |
| | | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |