aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-01-25Merge pull request #7201 from brkirch/update-macos-defaultsAUTOMATIC1111
Update default Mac command line arguments to use --upcast-sampling instead of --no-half
2023-01-25Update arguments to use --upcast-samplingbrkirch
2023-01-25fix for unet hijack breaking the train tabAUTOMATIC
2023-01-25make clicking extra networks button one more time close the extra networks UIAUTOMATIC
2023-01-25add pix2pix creditsAUTOMATIC
2023-01-25Merge pull request #6510 from brkirch/unet16-upcast-precisionAUTOMATIC1111
Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half
2023-01-25Merge pull request #7138 from mykeehu/patch-4AUTOMATIC1111
Fix extra network thumbs label color
2023-01-25change to code for live preview fix on OSX to be bit more obviousAUTOMATIC
2023-01-25Merge pull request #7151 from brkirch/fix-approx-nnAUTOMATIC1111
Fix Approx NN previews changing first generation result
2023-01-25Merge pull request #7195 from Klace/instruct-pix2pix_model_loadAUTOMATIC1111
Add instruct-pix2pix hijack
2023-01-25Update requirements transformers==4.25.1Kyle
Update requirement for transformers to version 4.25.1 to allow instruct-pix2pix demo code to work
2023-01-25Add instruct-pix2pix hijackKyle
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
2023-01-25Merge pull request #7146 from EllangoK/masterAUTOMATIC1111
Adds X/Y/Z Grid Script
2023-01-25add an experimental option to apply loras to outputs rather than inputsAUTOMATIC
2023-01-25Add UI setting for upcasting attention to float32brkirch
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.
2023-01-25Add option for float32 sampling with float16 UNetbrkirch
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().
2023-01-25remove the pip install stuff because it does not work as i hoped it wouldAUTOMATIC
2023-01-24add fastapi to requirementsAUTOMATIC
2023-01-24print progress when installing torchAUTOMATIC
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
2023-01-24remove fairscale requirement, add fake fairscale to make BLIP not complain ↵AUTOMATIC
about it mk2
2023-01-24remove fairscale requirement, add fake fairscale to make BLIP not complain ↵AUTOMATIC
about it
2023-01-24make git commands not fail for extensions when you have spaces in webui ↵AUTOMATIC
directory
2023-01-24swaps xyz axes internally if one costs moreEllangoK
2023-01-24handling sub grids and merging into oneEllangoK
2023-01-24implements most of xyz grid scriptEllangoK
2023-01-24renamed xy to xyz gridEllangoK
this is mostly just so git can detect it properly
2023-01-24also return the removed field to sdapi/v1/upscalers because someone might ↵AUTOMATIC
have relied on it existing
2023-01-24repair sdapi/v1/upscalers returning bogus resultsAUTOMATIC
2023-01-24Merge pull request #7140 from vladmandic/api-decode-imageAUTOMATIC1111
Add exception handling to API image decode
2023-01-24Merge pull request #7144 from catboxanon/swinir-interruptAUTOMATIC1111
Make SwinIR upscaler interruptible and skippable
2023-01-24Merge pull request #7148 from acncagua/improvement_launch.pyAUTOMATIC1111
Set Linux xformers 0.0.16RC425
2023-01-23Fix different first gen with Approx NN previewsbrkirch
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.
2023-01-24Set Linux xformers 0.0.16RC425acncagua
2023-01-23Also make SwinIR skippablecatboxanon
2023-01-23Make SwinIR interruptiblecatboxanon
2023-01-23add image decod exception handlingVladimir Mandic
2023-01-23Fix extra network thumbs label colorMykeehu
Added white color for labels.
2023-01-24fix BLIP failing to import depending on configurationAUTOMATIC
2023-01-24Merge pull request #7113 from vladmandic/interrogateAUTOMATIC1111
Add selector to interrogate categories
2023-01-23add support for apostrophe in extra network namesAUTOMATIC
2023-01-23suppress A matching Triton is not available messageAUTOMATIC
you can all now stop worrying about it
2023-01-23add option to skip interrogate categoriesVladimir Mandic
2023-01-23Merge branch 'AUTOMATIC1111:master' into interrogateVladimir Mandic
2023-01-23make loras before 0.4.0 ALSO workAUTOMATIC
2023-01-23Merge pull request #7032 from gmq/extra-network-stylesAUTOMATIC1111
Extra network view style
2023-01-23Merge pull request #7116 from vladmandic/api-image-formatAUTOMATIC1111
API should use same image format as specified in WebUI settings
2023-01-23feat(extra-networks): replace icon background with borderGuillermo Moreno
2023-01-23add support for loras trained on kohya's scripts 0.4.0 (alphas)AUTOMATIC
2023-01-23api-image-formatVladimir Mandic
2023-01-23a possible fix for broken image upscalingAUTOMATIC
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 15:32:00 +0000