Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | store patches for Lora in a specialized module | AUTOMATIC1111 | 2023-08-15 | 1 | -0/+64 |
| | |||||
* | Merge pull request #12570 from NoCrypt/add-miku-theme | AUTOMATIC1111 | 2023-08-15 | 1 | -1/+2 |
|\ | | | | | Add NoCrypt/miku gradio theme | ||||
| * | Add NoCrypt/miku gradio theme | NoCrypt | 2023-08-15 | 1 | -1/+2 |
| | | |||||
* | | Use the new SD VAE override setting | brkirch | 2023-08-15 | 1 | -1/+1 |
| | | |||||
* | | Merge pull request #12564 from catboxanon/feat/img2img-noise | AUTOMATIC1111 | 2023-08-15 | 3 | -1/+10 |
|\ \ | |/ |/| | Add extra noise param for img2img operations | ||||
| * | Add extra img2img noise | catboxanon | 2023-08-15 | 3 | -1/+10 |
| | | |||||
* | | fix processing error that happens if batch_size is not a multiple of how ↵ | AUTOMATIC1111 | 2023-08-15 | 1 | -1/+6 |
| | | | | | | | | many prompts/negative prompts there are #12509 | ||||
* | | get XYZ plot to work with recent changes to refined specified in fields of p ↵ | AUTOMATIC1111 | 2023-08-15 | 2 | -2/+2 |
| | | | | | | | | rather than in settings | ||||
* | | Merge pull request #12552 from brkirch/update-sdxl-commit-hash | AUTOMATIC1111 | 2023-08-15 | 1 | -1/+1 |
|\ \ | | | | | | | Update SD XL commit hash | ||||
| * | | Update hash for SD XL Repo | brkirch | 2023-08-14 | 1 | -1/+1 |
| | | | |||||
* | | | correctly add Eta DDIM to infotext when it's 1.0 and do not add it when it's ↵ | AUTOMATIC1111 | 2023-08-14 | 2 | -1/+3 |
| |/ |/| | | | | | 0.0. | ||||
* | | revert changed inpainting mask conditioning calculation after #12311 | AUTOMATIC1111 | 2023-08-14 | 1 | -1/+1 |
| | | |||||
* | | Merge pull request #12547 from whitebell/fix-typo | AUTOMATIC1111 | 2023-08-14 | 1 | -1/+1 |
|\ \ | |/ |/| | Fix typo in shared_options.py | ||||
| * | Fix typo in shared_options.py | whitebell | 2023-08-14 | 1 | -1/+1 |
| | | | | | | unperdictable -> unpredictable | ||||
* | | add second_order to samplers that mistakenly didn't have it | AUTOMATIC1111 | 2023-08-14 | 1 | -3/+3 |
| | | |||||
* | | fix API always using -1 as seed | AUTOMATIC1111 | 2023-08-14 | 5 | -6/+16 |
| | | |||||
* | | return seed controls UI to how it was before | AUTOMATIC1111 | 2023-08-14 | 1 | -18/+29 |
| | | |||||
* | | further repair the /docs page to not break styles with the attempted fix | AUTOMATIC1111 | 2023-08-14 | 1 | -1/+3 |
|/ | |||||
* | repair /docs page | AUTOMATIC1111 | 2023-08-14 | 2 | -5/+7 |
| | |||||
* | Merge pull request #12542 from AUTOMATIC1111/res-sampler | AUTOMATIC1111 | 2023-08-14 | 1 | -0/+10 |
|\ | | | | | Add RES sampler and reorder the sampler list | ||||
| * | Put frequently used sampler back | Kohaku-Blueleaf | 2023-08-14 | 1 | -4/+4 |
| | | |||||
| * | add res(dpmdd 2m sde heun) and reorder the sampler list | Kohaku-Blueleaf | 2023-08-14 | 1 | -4/+14 |
| | | |||||
* | | revert to applying mask before denoising for k-diffusion, like it was before | AUTOMATIC1111 | 2023-08-14 | 2 | -1/+6 |
| | | |||||
* | | make on_before_component/on_after_component possible earlier | AUTOMATIC1111 | 2023-08-14 | 1 | -10/+25 |
| | | |||||
* | | repair DDIM/PLMS/UniPC batches | AUTOMATIC1111 | 2023-08-14 | 2 | -11/+12 |
|/ | |||||
* | also use setup callback for the refiner instead of before_process | AUTOMATIC1111 | 2023-08-13 | 1 | -1/+1 |
| | |||||
* | Merge pull request #12526 from brkirch/mps-adjust-sub-quad | AUTOMATIC1111 | 2023-08-13 | 5 | -10/+17 |
|\ | | | | | Fixes for `git checkout`, MPS/macOS fixes and optimizations | ||||
| * | Fix DDIM and PLMS samplers on MPS | brkirch | 2023-08-13 | 1 | -2/+2 |
| | | |||||
| * | Remove duplicate code for torchsde randn | brkirch | 2023-08-13 | 1 | -3/+0 |
| | | |||||
| * | Change the repositories origin URLs when necessary | brkirch | 2023-08-13 | 1 | -0/+3 |
| | | |||||
| * | `git checkout` with commit hash | brkirch | 2023-08-13 | 1 | -1/+1 |
| | | |||||
| * | `torch.empty` can create issues; use `torch.zeros` | brkirch | 2023-08-13 | 1 | -2/+2 |
| | | | | | | | | 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. | ||||
| * | Make sub-quadratic the default for MPS | brkirch | 2023-08-13 | 1 | -2/+5 |
| | | |||||
| * | Use fixed size for sub-quadratic chunking on MPS | brkirch | 2023-08-13 | 1 | -1/+5 |
| | | | | | | | | 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. | ||||
* | | Merge pull request #12530 from eltociear/eltociear-patch-1 | AUTOMATIC1111 | 2023-08-13 | 1 | -1/+1 |
|\ \ | | | | | | | Fix typo in launch_utils.py | ||||
| * | | Fix typo in launch_utils.py | Ikko Eltociear Ashimine | 2023-08-13 | 1 | -1/+1 |
| | | | | | | | | | existance -> existence | ||||
* | | | fix 2 for git code botched by previous PRs | AUTOMATIC1111 | 2023-08-13 | 1 | -1/+1 |
| | | | |||||
* | | | fix broken XYZ plot seeds | AUTOMATIC1111 | 2023-08-13 | 3 | -4/+47 |
| |/ |/| | | | | | add new callback for scripts to be used before processing | ||||
* | | fix for the broken run_git calls | AUTOMATIC1111 | 2023-08-13 | 1 | -2/+2 |
| | | |||||
* | | Merge pull request #12510 from catboxanon/feat/extnet/hashes | AUTOMATIC1111 | 2023-08-13 | 4 | -3/+11 |
|\ \ | | | | | | | Support search and display of hashes for all extra network items | ||||
| * | | Support search and display of hashes for all extra network items | catboxanon | 2023-08-13 | 4 | -3/+11 |
| | | | |||||
* | | | Merge pull request #12515 from catboxanon/fix/gc1 | AUTOMATIC1111 | 2023-08-13 | 1 | -0/+3 |
|\ \ \ | | | | | | | | | Clear sampler and garbage collect before decoding images to reduce VRAM | ||||
| * | | | Clear sampler before decoding images | catboxanon | 2023-08-13 | 1 | -0/+3 |
| |/ / | | | | | | | | | | More significant VRAM reduction. | ||||
* | | | Merge pull request #12514 from catboxanon/feat/batch-encode | AUTOMATIC1111 | 2023-08-13 | 1 | -1/+9 |
|\ \ \ | | | | | | | | | Encode batch items individually to significantly reduce VRAM | ||||
| * | | | Encode batches separately | catboxanon | 2023-08-13 | 1 | -1/+9 |
| |/ / | | | | | | | | | | | | | Significantly reduces VRAM. This makes encoding more inline with how decoding currently functions. | ||||
* | | | Merge pull request #12520 from catboxanon/eta | AUTOMATIC1111 | 2023-08-13 | 1 | -1/+1 |
|\ \ \ | | | | | | | | | Update description of eta setting | ||||
| * | | | Update description of eta setting | catboxanon | 2023-08-13 | 1 | -1/+1 |
| |/ / | |||||
* | | | Merge pull request #12521 from catboxanon/feat/more-s-noise | AUTOMATIC1111 | 2023-08-13 | 4 | -6/+15 |
|\ \ \ | | | | | | | | | Add `s_noise` param to more samplers | ||||
| * \ \ | Merge branch 'feat/dpmpp3msde' into feat/more-s-noise | catboxanon | 2023-08-13 | 1 | -3/+3 |
| |\ \ \ | |||||
| | * | | | Discard penultimate sigma for DPM-Solver++(3M) SDE | catboxanon | 2023-08-13 | 1 | -3/+3 |
| | | | | |