| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2023-08-14 | Merge pull request #12543 from AUTOMATIC1111/extra-norm-module | AUTOMATIC1111 | |
| Fix MHA error with ex_bias and support ex_bias for layers which don't have bias | |||
| 2023-08-14 | revert to applying mask before denoising for k-diffusion, like it was before | AUTOMATIC1111 | |
| 2023-08-14 | remove "if bias exist" check | Kohaku-Blueleaf | |
| 2023-08-14 | make on_before_component/on_after_component possible earlier | AUTOMATIC1111 | |
| 2023-08-14 | repair DDIM/PLMS/UniPC batches | AUTOMATIC1111 | |
| 2023-08-14 | Merge branch 'dev' into extra-norm-module | Kohaku-Blueleaf | |
| 2023-08-14 | Fix MHA updown err and support ex-bias for no-bias layer | Kohaku-Blueleaf | |
| 2023-08-13 | also use setup callback for the refiner instead of before_process | AUTOMATIC1111 | |
| 2023-08-13 | Merge pull request #12526 from brkirch/mps-adjust-sub-quad | AUTOMATIC1111 | |
| Fixes for `git checkout`, MPS/macOS fixes and optimizations | |||
| 2023-08-13 | Merge pull request #12530 from eltociear/eltociear-patch-1 | AUTOMATIC1111 | |
| Fix typo in launch_utils.py | |||
| 2023-08-13 | fix 2 for git code botched by previous PRs | AUTOMATIC1111 | |
| 2023-08-14 | Fix typo in launch_utils.py | Ikko Eltociear Ashimine | |
| existance -> existence | |||
| 2023-08-13 | fix broken XYZ plot seeds | AUTOMATIC1111 | |
| add new callback for scripts to be used before processing | |||
| 2023-08-13 | Fix DDIM and PLMS samplers on MPS | brkirch | |
| 2023-08-13 | Remove duplicate code for torchsde randn | brkirch | |
| 2023-08-13 | Mac k-diffusion workarounds are no longer needed | brkirch | |
| 2023-08-13 | Change the repositories origin URLs when necessary | brkirch | |
| 2023-08-13 | `git checkout` with commit hash | brkirch | |
| 2023-08-13 | `torch.empty` can create issues; use `torch.zeros` | brkirch | |
| For MPS, using a tensor created with `torch.empty()` can cause `torch.baddbmm()` to include NaNs in the tensor it returns, even though `beta=0`. However, with a tensor of shape [1,1,1], there should be a negligible performance difference between `torch.empty()` and `torch.zeros()` anyway, so it's better to just use `torch.zeros()` for this and avoid unnecessarily creating issues. | |||
| 2023-08-13 | Make sub-quadratic the default for MPS | brkirch | |
| 2023-08-13 | Use fixed size for sub-quadratic chunking on MPS | brkirch | |
| Even if this causes chunks to be much smaller, performance isn't significantly impacted. This will usually reduce memory usage but should also help with poor performance when free memory is low. | |||
| 2023-08-13 | fix for the broken run_git calls | AUTOMATIC1111 | |
| 2023-08-13 | Merge pull request #12510 from catboxanon/feat/extnet/hashes | AUTOMATIC1111 | |
| Support search and display of hashes for all extra network items | |||
| 2023-08-13 | Merge pull request #12515 from catboxanon/fix/gc1 | AUTOMATIC1111 | |
| Clear sampler and garbage collect before decoding images to reduce VRAM | |||
| 2023-08-13 | Merge pull request #12514 from catboxanon/feat/batch-encode | AUTOMATIC1111 | |
| Encode batch items individually to significantly reduce VRAM | |||
| 2023-08-13 | Merge pull request #12520 from catboxanon/eta | AUTOMATIC1111 | |
| Update description of eta setting | |||
| 2023-08-13 | Merge pull request #12521 from catboxanon/feat/more-s-noise | AUTOMATIC1111 | |
| Add `s_noise` param to more samplers | |||
| 2023-08-13 | Merge pull request #12522 from catboxanon/fix/extra_params | AUTOMATIC1111 | |
| Restore `extra_params` that was lost in merge | |||
| 2023-08-13 | linter | AUTOMATIC1111 | |
| 2023-08-13 | Restore extra_params that was lost in merge | catboxanon | |
| 2023-08-13 | Merge branch 'feat/dpmpp3msde' into feat/more-s-noise | catboxanon | |
| 2023-08-13 | Discard penultimate sigma for DPM-Solver++(3M) SDE | catboxanon | |
| 2023-08-13 | Fix s_noise description | catboxanon | |
| 2023-08-13 | Add s_noise param to more samplers | catboxanon | |
| 2023-08-13 | Lora: output warnings in UI rather than fail for unfitting loras; switch to ↵ | AUTOMATIC1111 | |
| logging for error output in console | |||
| 2023-08-13 | Update description of eta setting | catboxanon | |
| 2023-08-13 | Add DPM-Solver++(3M) SDE | catboxanon | |
| 2023-08-13 | Clear sampler before decoding images | catboxanon | |
| More significant VRAM reduction. | |||
| 2023-08-13 | Encode batches separately | catboxanon | |
| Significantly reduces VRAM. This makes encoding more inline with how decoding currently functions. | |||
| 2023-08-13 | Support search and display of hashes for all extra network items | catboxanon | |
| 2023-08-13 | Merge pull request #12503 from AUTOMATIC1111/extra-norm-module | AUTOMATIC1111 | |
| Add Norm Module to lora ext and add "bias" support | |||
| 2023-08-13 | Merge pull request #12491 from AUTOMATIC1111/xyz-csv-and-dropdown-mode | AUTOMATIC1111 | |
| Bring back CSV mode for XYZ grid | |||
| 2023-08-13 | use dataclass for StableDiffusionProcessing | AUTOMATIC1111 | |
| 2023-08-13 | rephrase and move | w-e-w | |
| 2023-08-13 | add refiner to StableDiffusionProcessing class | AUTOMATIC1111 | |
| write out correct model name in infotext, rather than the refiner model | |||
| 2023-08-13 | remove debug print | Kohaku-Blueleaf | |
| 2023-08-13 | return None if no ex_bias | Kohaku-Blueleaf | |
| 2023-08-13 | Add extra norm module into built-in lora ext | Kohaku-Blueleaf | |
| refer to LyCORIS 1.9.0.dev6 add new option and module for training norm layer (Which is reported to be good for style) | |||
| 2023-08-13 | properly convert this into CSV string | w-e-w | |
| 2023-08-13 | pass csv_mode | w-e-w | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |