Age | Commit message (Collapse) | Author | Lines | |
---|---|---|---|---|
2023-01-25 | Add option for float32 sampling with float16 UNet | brkirch | -8/+82 | |
This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half(). | ||||
2023-01-25 | remove the pip install stuff because it does not work as i hoped it would | AUTOMATIC | -8/+11 | |
2023-01-24 | add fastapi to requirements | AUTOMATIC | -0/+1 | |
2023-01-24 | print progress when installing torch | AUTOMATIC | -6/+22 | |
add PIP_INSTALLER_LOCATION env var to install pip if it's not installed remove accidental call to accelerate when venv is disabled add another env var to skip venv - SKIP_VENV | ||||
2023-01-24 | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | -1/+1 | |
about it mk2 | ||||
2023-01-24 | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | -4/+9 | |
about it | ||||
2023-01-24 | make git commands not fail for extensions when you have spaces in webui ↵ | AUTOMATIC | -4/+4 | |
directory | ||||
2023-01-24 | also return the removed field to sdapi/v1/upscalers because someone might ↵ | AUTOMATIC | -0/+2 | |
have relied on it existing | ||||
2023-01-24 | repair sdapi/v1/upscalers returning bogus results | AUTOMATIC | -8/+10 | |
2023-01-24 | Merge pull request #7140 from vladmandic/api-decode-image | AUTOMATIC1111 | -1/+5 | |
Add exception handling to API image decode | ||||
2023-01-24 | Merge pull request #7144 from catboxanon/swinir-interrupt | AUTOMATIC1111 | -1/+7 | |
Make SwinIR upscaler interruptible and skippable | ||||
2023-01-24 | Merge pull request #7148 from acncagua/improvement_launch.py | AUTOMATIC1111 | -1/+1 | |
Set Linux xformers 0.0.16RC425 | ||||
2023-01-24 | Set Linux xformers 0.0.16RC425 | acncagua | -1/+1 | |
2023-01-23 | Also make SwinIR skippable | catboxanon | -2/+2 | |
2023-01-23 | Make SwinIR interruptible | catboxanon | -1/+7 | |
2023-01-23 | add image decod exception handling | Vladimir Mandic | -1/+5 | |
2023-01-24 | fix BLIP failing to import depending on configuration | AUTOMATIC | -1/+16 | |
2023-01-24 | Merge pull request #7113 from vladmandic/interrogate | AUTOMATIC1111 | -16/+26 | |
Add selector to interrogate categories | ||||
2023-01-23 | add support for apostrophe in extra network names | AUTOMATIC | -4/+6 | |
2023-01-23 | suppress A matching Triton is not available message | AUTOMATIC | -1/+3 | |
you can all now stop worrying about it | ||||
2023-01-23 | add option to skip interrogate categories | Vladimir Mandic | -15/+19 | |
2023-01-23 | Merge branch 'AUTOMATIC1111:master' into interrogate | Vladimir Mandic | -27/+140 | |
2023-01-23 | make loras before 0.4.0 ALSO work | AUTOMATIC | -1/+2 | |
2023-01-23 | Merge pull request #7032 from gmq/extra-network-styles | AUTOMATIC1111 | -4/+73 | |
Extra network view style | ||||
2023-01-23 | Merge pull request #7116 from vladmandic/api-image-format | AUTOMATIC1111 | -10/+24 | |
API should use same image format as specified in WebUI settings | ||||
2023-01-23 | feat(extra-networks): replace icon background with border | Guillermo Moreno | -2/+5 | |
2023-01-23 | add support for loras trained on kohya's scripts 0.4.0 (alphas) | AUTOMATIC | -7/+11 | |
2023-01-23 | api-image-format | Vladimir Mandic | -10/+24 | |
2023-01-23 | a possible fix for broken image upscaling | AUTOMATIC | -1/+1 | |
2023-01-23 | add a message about new torch/xformers version and a way to upgrade by ↵ | AUTOMATIC | -1/+28 | |
specifying a commandline flag | ||||
2023-01-23 | Merge pull request #5939 from petalas/petalas/torch-upgrade | AUTOMATIC1111 | -4/+2 | |
upgrading torch, torchvision, xformers (windows), to use cu117 | ||||
2023-01-23 | improve interrogate | Vladimir Mandic | -12/+18 | |
2023-01-23 | better support for xformers flash attention on older versions of torch | AUTOMATIC | -24/+30 | |
2023-01-23 | Merge remote-tracking branch 'takuma104/xformers-flash-attention' | AUTOMATIC | -2/+25 | |
2023-01-23 | fix open directory button failing | AUTOMATIC | -2/+1 | |
2023-01-23 | Merge pull request #7081 from EllangoK/xy-hires | AUTOMATIC1111 | -3/+15 | |
Adds Hires Steps to X/Y Plot, and updates step calculation | ||||
2023-01-23 | Merge pull request #7031 from EllangoK/master | AUTOMATIC1111 | -3/+11 | |
Fixes various button overflowing UI and compact checkbox | ||||
2023-01-23 | Merge pull request #7093 from Shondoit/fix-dark-mode | AUTOMATIC1111 | -2/+2 | |
Fix dark mode | ||||
2023-01-23 | third time's the charm | AUTOMATIC | -1/+1 | |
2023-01-23 | add missing import to previous commit | AUTOMATIC | -0/+1 | |
2023-01-23 | Fix dark mode | Shondoit | -2/+2 | |
Fixes #7048 Co-Authored-By: J.J. Tolton <jjtolton@gmail.com> | ||||
2023-01-23 | rework extras tab to use script system | AUTOMATIC | -464/+675 | |
2023-01-22 | feat(extra-networks): remove view dropdown | Guillermo Moreno | -13/+9 | |
2023-01-22 | adds hires steps to x/y plot and fixes total_steps calculation | EllangoK | -3/+15 | |
2023-01-22 | feat(extra-networks): add default view setting | Guillermo Moreno | -4/+8 | |
2023-01-22 | feat(extra-networks): add thumbs view style | Guillermo Moreno | -12/+78 | |
2023-01-22 | split oversize extras.py to postprocessing.py | AUTOMATIC | -474/+18 | |
2023-01-22 | Split history extras.py to postprocessing.py | Andrey | -0/+0 | |
2023-01-22 | Split history extras.py to postprocessing.py | Andrey | -0/+466 | |
2023-01-22 | Split history extras.py to postprocessing.py | Andrey | -0/+0 | |