| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | Fix SD VAE switch error after model reuse | Uminosachi | 2023-08-20 | 1 | -2/+20 | |
| | | ||||||
| * | resolve the issue with loading fp16 checkpoints while using --no-half | AUTOMATIC1111 | 2023-08-17 | 1 | -1/+4 | |
| | | ||||||
| * | send weights to target device instead of CPU memory | AUTOMATIC1111 | 2023-08-16 | 1 | -1/+16 | |
| | | ||||||
| * | Revert "send weights to target device instead of CPU memory" | AUTOMATIC1111 | 2023-08-16 | 1 | -1/+1 | |
| | | | | | This reverts commit 0815c45bcdec0a2e5c60bdd5b33d95813d799c01. | |||||
| * | send weights to target device instead of CPU memory | AUTOMATIC1111 | 2023-08-16 | 1 | -1/+1 | |
| | | ||||||
| * | put refiner into main UI, into the new accordions section | AUTOMATIC1111 | 2023-08-12 | 1 | -0/+3 | |
| | | | | | | | add VAE from main model into infotext, not from refiner model option to make scripts UI without gr.Group fix inconsistencies with refiner when usings samplers that do more denoising than steps | |||||
| * | resolve merge issues | AUTOMATIC1111 | 2023-08-10 | 1 | -2/+5 | |
| | | ||||||
| * | Merge branch 'dev' into refiner | AUTOMATIC1111 | 2023-08-10 | 1 | -11/+12 | |
| |\ | ||||||
| | * | fix checkpoint name jumping around in the list of checkpoints for no good reason | AUTOMATIC1111 | 2023-08-09 | 1 | -3/+9 | |
| | | | ||||||
| | * | Merge pull request #12426 from AUTOMATIC1111/split_shared | AUTOMATIC1111 | 2023-08-09 | 1 | -8/+1 | |
| | |\ | | | | | | | Split shared.py into multiple files | |||||
| | | * | split shared.py into multiple files; should resolve all circular reference ↵ | AUTOMATIC1111 | 2023-08-09 | 1 | -8/+1 | |
| | | | | | | | | | | | | | import errors related to shared.py | |||||
| | * | | Fix mismatch between shared.sd_model & shared.opts | Uminosachi | 2023-08-08 | 1 | -0/+2 | |
| | |/ | ||||||
| * | | Merge branch 'dev' into refiner | AUTOMATIC1111 | 2023-08-08 | 1 | -1/+2 | |
| |\| | ||||||
| | * | apply unet overrides after switching model | AUTOMATIC1111 | 2023-08-07 | 1 | -0/+1 | |
| | | | ||||||
| | * | SD VAE rework 2 | AUTOMATIC1111 | 2023-08-07 | 1 | -1/+1 | |
| | | | | | | | | | | | | | | | - the setting for preferring opts.sd_vae has been inverted and reworded - resolve_vae function made easier to read and now returns an object rather than a tuple - if the checkbox for overriding per-model preferences is checked, opts.sd_vae overrides checkpoint user metadata - changing VAE in user metadata for currently loaded model immediately applies the selection | |||||
| * | | initial refiner support | AUTOMATIC1111 | 2023-08-06 | 1 | -1/+17 | |
| |/ | ||||||
| * | Merge branch 'dev' into multiple_loaded_models | AUTOMATIC1111 | 2023-08-05 | 1 | -12/+17 | |
| |\ | ||||||
| | * | Merge pull request #12181 from AUTOMATIC1111/hires_checkpoint | AUTOMATIC1111 | 2023-08-05 | 1 | -10/+17 | |
| | |\ | | | | | | | Hires fix change checkpoint | |||||
| | | * | additional memory improvements when switching between models of different types | AUTOMATIC1111 | 2023-07-31 | 1 | -1/+4 | |
| | | | | ||||||
| | | * | hires fix checkpoint selection | AUTOMATIC1111 | 2023-07-30 | 1 | -9/+13 | |
| | | | | ||||||
| | * | | fix: prevent cache model.state_dict() after model hijack | AnyISalIn | 2023-08-04 | 1 | -2/+3 | |
| | | | | | | | | | | | | | Signed-off-by: AnyISalIn <anyisalin@gmail.com> | |||||
| | * | | add style editor dialog | AUTOMATIC1111 | 2023-08-03 | 1 | -1/+1 | |
| | | | | | | | | | | | | | | | | rework toprow for img2img and txt2img to use a class with fields fix the console error when editing checkpoint user metadata | |||||
| * | | | repair merge error | AUTOMATIC1111 | 2023-08-01 | 1 | -1/+0 | |
| | | | | ||||||
| * | | | Merge branch 'dev' into multiple_loaded_models | AUTOMATIC1111 | 2023-08-01 | 1 | -11/+18 | |
| |\| | | ||||||
| | * | | add metadata to checkpoint merger | AUTOMATIC1111 | 2023-08-01 | 1 | -1/+1 | |
| | | | | ||||||
| | * | | show metadata for SD checkpoints in the extra networks UI | AUTOMATIC1111 | 2023-08-01 | 1 | -10/+16 | |
| | |/ | ||||||
| * / | option to keep multiple models in memory | AUTOMATIC1111 | 2023-07-31 | 1 | -24/+112 | |
| |/ | ||||||
| * | Use less RAM when creating models | AUTOMATIC1111 | 2023-07-24 | 1 | -6/+10 | |
| | | ||||||
| * | fix the issue with /sdapi/v1/options failing (this time for sure!) | AUTOMATIC1111 | 2023-07-18 | 1 | -1/+1 | |
| | | | | | fix automated tests downloading CLIP model | |||||
| * | Add support for `--upcast-sampling` with SD XL | brkirch | 2023-07-18 | 1 | -1/+1 | |
| | | ||||||
| * | hide cards for networks of incompatible stable diffusion version in Lora ↵ | AUTOMATIC1111 | 2023-07-17 | 1 | -0/+3 | |
| | | | | | extra networks interface | |||||
| * | linter | AUTOMATIC1111 | 2023-07-14 | 1 | -1/+1 | |
| | | ||||||
| * | initial SDXL refiner support | AUTOMATIC1111 | 2023-07-14 | 1 | -1/+2 | |
| | | ||||||
| * | add support for SDXL loras with te1/te2 modules | AUTOMATIC1111 | 2023-07-13 | 1 | -1/+2 | |
| | | ||||||
| * | repair --no-half for SDXL | AUTOMATIC1111 | 2023-07-13 | 1 | -4/+5 | |
| | | ||||||
| * | SDXL support | AUTOMATIC1111 | 2023-07-12 | 1 | -2/+12 | |
| | | ||||||
| * | getting SD2.1 to run on SDXL repo | AUTOMATIC1111 | 2023-07-11 | 1 | -2/+6 | |
| | | ||||||
| * | Fix typo: checkpoint_alisases | Aarni Koskela | 2023-07-08 | 1 | -5/+6 | |
| | | ||||||
| * | added torch.mps.empty_cache() to torch_gc() | AUTOMATIC1111 | 2023-07-08 | 1 | -1/+0 | |
| | | | | | changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead | |||||
| * | send tensors to the correct device when loading from safetensors file with ↵ | AUTOMATIC | 2023-06-27 | 1 | -1/+3 | |
| | | | | | memmap disabled for #11260 | |||||
| * | Merge pull request #11260 from dhwz/dev | AUTOMATIC1111 | 2023-06-27 | 1 | -2/+5 | |
| |\ | | | | | fix very slow loading speed of .safetensors files | |||||
| | * | fix very slow loading speed of .safetensors files | dhwz | 2023-06-16 | 1 | -2/+5 | |
| | | | ||||||
| * | | Use os.makedirs(..., exist_ok=True) | Aarni Koskela | 2023-06-13 | 1 | -2/+1 | |
| |/ | ||||||
| * | assign devices.dtype early because it's needed before the model is loaded | AUTOMATIC | 2023-06-01 | 1 | -2/+0 | |
| | | ||||||
| * | Merge pull request #10739 from linkoid/fix-ui-debug-mode-exit | AUTOMATIC1111 | 2023-05-27 | 1 | -7/+8 | |
| |\ | | | | | Fix --ui-debug-mode exit | |||||
| | * | Show full traceback in get_sd_model() | linkoid | 2023-05-26 | 1 | -1/+1 | |
| | | | | | | | | | to reveal if an error is caused by an extension | |||||
| | * | Remove exit() from select_checkpoint() | linkoid | 2023-05-26 | 1 | -6/+7 | |
| | | | | | | | | | Raising a FileNotFoundError instead. | |||||
| * | | custom unet support | AUTOMATIC | 2023-05-27 | 1 | -1/+3 | |
| |/ | ||||||
| * | option to pad prompt/neg prompt to be same length | AUTOMATIC | 2023-05-21 | 1 | -0/+5 | |
| | | ||||||
| * | Deduplicate webui.py initial-load/reload code | Aarni Koskela | 2023-05-19 | 1 | -1/+0 | |
| | | ||||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |