aboutsummaryrefslogtreecommitdiff
path: root/modules/shared.py
AgeCommit message (Collapse)Author
2023-01-30Add --skip-version-check to disable messages asking users to upgrade torch.AUTOMATIC
2023-01-30change disable_weights_auto_swap to true by defaultAUTOMATIC
2023-01-30make it so that setting options in pasted infotext (like Clip Skip and ENSD) ↵AUTOMATIC
do not get applied directly and instead are added as temporary overrides
2023-01-28add dropdowns in settings for hypernets and lorasAUTOMATIC
2023-01-27add data-dir flag and set all user data directories based on itMax Audron
2023-01-27remove the need to place configs near modelsAUTOMATIC
2023-01-26add an option to enable sections from extras tab in txt2img/img2imgAUTOMATIC
fix some style inconsistenices
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().
2023-01-23add option to skip interrogate categoriesVladimir Mandic
2023-01-23Merge branch 'AUTOMATIC1111:master' into interrogateVladimir Mandic
2023-01-23Merge pull request #7032 from gmq/extra-network-stylesAUTOMATIC1111
Extra network view style
2023-01-23improve interrogateVladimir Mandic
2023-01-23Merge remote-tracking branch 'takuma104/xformers-flash-attention'AUTOMATIC
2023-01-23rework extras tab to use script systemAUTOMATIC
2023-01-22feat(extra-networks): add default view settingGuillermo Moreno
2023-01-22add an option to reorder tabs for extra networksAUTOMATIC
2023-01-22attention ctrl+up/down enhancementsAUTOMATIC
2023-01-22add a slider for default value of added extra networksAUTOMATIC
2023-01-21add --gradio-queue option to enable gradio queueAUTOMATIC
2023-01-21add --xformers-flash-attention option & implTakuma Mori
2023-01-21make CLIP interrogator download original text files if the directory does ↵AUTOMATIC
not exist remove random artist built-in extension (to re-added as a normal extension on demand) remove artists.csv (but what does it mean????????????????????) make interrogate buttons show Loading... when you click them
2023-01-21extra networks UIAUTOMATIC
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
2023-01-19Update shared.pyvt-idiot
`Witdth/Height` was driving me insane. -> `Width/Height`
2023-01-19allow baking in VAE in checkpoint merger tabAUTOMATIC
do not save config if it's the default for checkpoint merger tab change file naming scheme for checkpoint merger tab allow just saving A without any merging for checkpoint merger tab some stylistic changes for UI in checkpoint merger tab
2023-01-18Merge pull request #6851 from ddPn08/masterAUTOMATIC1111
Add `--vae-dir` argument
2023-01-18add option to show/hide warningsAUTOMATIC
removed hiding warnings from LDSR fixed/reworked few places that produced warnings
2023-01-18fix typoddPn08
2023-01-17Add `--vae-dir` argumentddPn08
2023-01-17disable the new NaN check for the CIAUTOMATIC
2023-01-16return an option to hide progressbarAUTOMATIC
2023-01-16support old configs that say "auto" for ssd_vaeAUTOMATIC
change sd_vae_as_default to True by default as it's a more sensible setting
2023-01-15rename masking to inpaint in UIAUTOMATIC
make inpaint go to the right place for users who don't have it in config string
2023-01-15Merge pull request #6758 from Poktay/allow_reorder_masking_controlsAUTOMATIC1111
allow reordering of inpaint masking controls (like the other sections can be reordered)
2023-01-15Merge pull request #6778 from pangbo13/masterAUTOMATIC1111
Fix unexpected behavior when show_progress_every_n_steps is set to -1
2023-01-15add setting for progressbar update periodAUTOMATIC
2023-01-16fix when show_progress_every_n_steps == -1pangbo13
2023-01-15big rework of progressbar/preview system to allow multiple users to prompts ↵AUTOMATIC
at the same time and do not get previews of each other
2023-01-14add inpaint masking controls to orderable section that the settings can orderJosh R
2023-01-14Merge pull request #6731 from vladmandic/state_server_startVladimir Mandic
Add server start time to state info
2023-01-14fix bug with "Ignore selected VAE for..." option completely disabling VAE ↵AUTOMATIC
election rework VAE resolving code to be more simple
2023-01-14add server_start to shared.stateVladimir Mandic
2023-01-14add an option to choose what you want to see in live preview (Live preview ↵AUTOMATIC
subject) and moves live preview settings to its own tab
2023-01-14load hashes from cache for checkpoints that have themAUTOMATIC
add checkpoint hash to footer
2023-01-14change hypernets to use sha256 hashesAUTOMATIC
2023-01-14change hash to sha256AUTOMATIC
2023-01-13Merge branch 'master' into tensorboardAUTOMATIC1111
2023-01-11img2img UI rework: obsolete --gradio-img2img-tool --gradio-inpaint-tool and ↵AUTOMATIC
always show all tools each in own tab
2023-01-10change color selector in settings to be part of formAUTOMATIC
2023-01-09make a dropdown for prompt template selectionAUTOMATIC
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-29 15:01:37 +0000