aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Update arguments to use --upcast-samplingbrkirch2023-01-251-1/+1
|
* fix for unet hijack breaking the train tabAUTOMATIC2023-01-251-2/+5
|
* make clicking extra networks button one more time close the extra networks UIAUTOMATIC2023-01-251-2/+7
|
* add pix2pix creditsAUTOMATIC2023-01-251-1/+2
|
* Merge pull request #6510 from brkirch/unet16-upcast-precisionAUTOMATIC11112023-01-2510-71/+189
|\ | | | | Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half
| * Add UI setting for upcasting attention to float32brkirch2023-01-255-64/+108
| | | | | | | | | | | | Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers. In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also.
| * Add option for float32 sampling with float16 UNetbrkirch2023-01-258-8/+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().
* | Merge pull request #7138 from mykeehu/patch-4AUTOMATIC11112023-01-251-0/+1
|\ \ | | | | | | Fix extra network thumbs label color
| * | Fix extra network thumbs label colorMykeehu2023-01-231-0/+1
| | | | | | | | | Added white color for labels.
* | | change to code for live preview fix on OSX to be bit more obviousAUTOMATIC2023-01-251-2/+2
| | |
* | | Merge pull request #7151 from brkirch/fix-approx-nnAUTOMATIC11112023-01-251-1/+5
|\ \ \ | | | | | | | | Fix Approx NN previews changing first generation result
| * | | Fix different first gen with Approx NN previewsbrkirch2023-01-241-1/+5
| |/ / | | | | | | | | | The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance.
* | | Merge pull request #7195 from Klace/instruct-pix2pix_model_loadAUTOMATIC11112023-01-255-3/+1485
|\ \ \ | | | | | | | | Add instruct-pix2pix hijack
| * | | Update requirements transformers==4.25.1Kyle2023-01-252-2/+2
| | | | | | | | | | | | | | | | Update requirement for transformers to version 4.25.1 to allow instruct-pix2pix demo code to work
| * | | Add instruct-pix2pix hijackKyle2023-01-253-1/+1483
|/ / / | | | | | | | | | | | | | | | Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py Adds ddpm_edit.py necessary for instruct-pix2pix
* | | Merge pull request #7146 from EllangoK/masterAUTOMATIC11112023-01-252-45/+134
|\ \ \ | | | | | | | | Adds X/Y/Z Grid Script
| * | | swaps xyz axes internally if one costs moreEllangoK2023-01-241-12/+52
| | | |
| * | | handling sub grids and merging into oneEllangoK2023-01-242-12/+19
| | | |
| * | | implements most of xyz grid scriptEllangoK2023-01-241-36/+78
| | | |
| * | | renamed xy to xyz gridEllangoK2023-01-241-0/+0
| | | | | | | | | | | | | | | | this is mostly just so git can detect it properly
* | | | add an experimental option to apply loras to outputs rather than inputsAUTOMATIC2023-01-252-2/+10
| |_|/ |/| |
* | | remove the pip install stuff because it does not work as i hoped it wouldAUTOMATIC2023-01-243-8/+11
| | |
* | | add fastapi to requirementsAUTOMATIC2023-01-241-0/+1
| | |
* | | print progress when installing torchAUTOMATIC2023-01-242-6/+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
* | | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵AUTOMATIC2023-01-241-1/+1
| | | | | | | | | | | | about it mk2
* | | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵AUTOMATIC2023-01-243-4/+9
| | | | | | | | | | | | about it
* | | make git commands not fail for extensions when you have spaces in webui ↵AUTOMATIC2023-01-241-4/+4
| | | | | | | | | | | | directory
* | | also return the removed field to sdapi/v1/upscalers because someone might ↵AUTOMATIC2023-01-242-0/+2
| | | | | | | | | | | | have relied on it existing
* | | repair sdapi/v1/upscalers returning bogus resultsAUTOMATIC2023-01-242-8/+10
| | |
* | | Merge pull request #7140 from vladmandic/api-decode-imageAUTOMATIC11112023-01-241-1/+5
|\ \ \ | | | | | | | | Add exception handling to API image decode
| * | | add image decod exception handlingVladimir Mandic2023-01-231-1/+5
| | |/ | |/|
* | | Merge pull request #7144 from catboxanon/swinir-interruptAUTOMATIC11112023-01-241-1/+7
|\ \ \ | | | | | | | | Make SwinIR upscaler interruptible and skippable
| * | | Also make SwinIR skippablecatboxanon2023-01-241-2/+2
| | | |
| * | | Make SwinIR interruptiblecatboxanon2023-01-241-1/+7
| |/ /
* | | Merge pull request #7148 from acncagua/improvement_launch.pyAUTOMATIC11112023-01-241-1/+1
|\ \ \ | |/ / |/| | Set Linux xformers 0.0.16RC425
| * | Set Linux xformers 0.0.16RC425acncagua2023-01-241-1/+1
|/ /
* | fix BLIP failing to import depending on configurationAUTOMATIC2023-01-232-1/+16
| |
* | Merge pull request #7113 from vladmandic/interrogateAUTOMATIC11112023-01-232-16/+26
|\ \ | | | | | | Add selector to interrogate categories
| * | add option to skip interrogate categoriesVladimir Mandic2023-01-232-15/+19
| | |
| * | Merge branch 'AUTOMATIC1111:master' into interrogateVladimir Mandic2023-01-239-27/+140
| |\|
| * | improve interrogateVladimir Mandic2023-01-232-12/+18
| | |
* | | add support for apostrophe in extra network namesAUTOMATIC2023-01-232-4/+6
| | |
* | | suppress A matching Triton is not available messageAUTOMATIC2023-01-231-1/+3
| |/ |/| | | | | you can all now stop worrying about it
* | make loras before 0.4.0 ALSO workAUTOMATIC2023-01-231-1/+2
| |
* | Merge pull request #7032 from gmq/extra-network-stylesAUTOMATIC11112023-01-234-4/+73
|\ \ | | | | | | Extra network view style
| * | feat(extra-networks): replace icon background with borderGuillermo Moreno2023-01-232-2/+5
| | |
| * | feat(extra-networks): remove view dropdownGuillermo Moreno2023-01-232-13/+9
| | |
| * | feat(extra-networks): add default view settingGuillermo Moreno2023-01-222-4/+8
| | |
| * | feat(extra-networks): add thumbs view styleGuillermo Moreno2023-01-224-12/+78
| | |
* | | Merge pull request #7116 from vladmandic/api-image-formatAUTOMATIC11112023-01-231-10/+24
|\ \ \ | | | | | | | | API should use same image format as specified in WebUI settings
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-03 17:08:57 +0000