aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
* Merge pull request #7199 from maxaudron/feature/configurable-data-dirAUTOMATIC11112023-01-2816-38/+46
|\ | | | | Add flag to store user data sepperate from source code
| * create user extensions directory if not existsMax Audron2023-01-271-0/+2
| |
| * clean up unused script_path importsMax Audron2023-01-272-2/+2
| |
| * use python importlib to load and execute extension modulesMax Audron2023-01-271-6/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | previously module attributes like __file__ where not set correctly, leading to scripts getting the directory of the stable-diffusion repo location instead of their own script. This causes problem when loading user data from an external location using the --data-dir flag, as extensions would look for their own code in the stable-diffusion repo location instead of the data dir location. Using pythons importlib functions sets the modules specs correctly and executes them. But this will break extensions if they build paths based on the previously incorrect __file__ attribute.
| * add data-dir flag and set all user data directories based on itMax Audron2023-01-2714-31/+39
| |
* | simplify #7284AUTOMATIC2023-01-281-8/+3
| |
* | Merge pull request #7284 from Gazzoo-byte/patch-1AUTOMATIC11112023-01-281-0/+11
|\ \ | | | | | | Add button to switch width and height
| * | Add button to switch width and heightGazzoo-byte2023-01-271-0/+11
| |/ | | | | Adds a button to switch width and height, allowing quick and easy switching between landscape and portrait.
* | make the detection for -v models less broadAUTOMATIC2023-01-281-1/+1
| |
* | Merge pull request #7294 from MrCheeze/model-detectionAUTOMATIC11112023-01-281-1/+4
|\ \ | | | | | | add v2-inpainting model detection, and broaden v-model detection to include anything with 768 in the name
| * | add v2-inpainting model detection, and broaden v-model detection to include ↵MrCheeze2023-01-281-1/+4
| | | | | | | | | | | | anything with 768 in the name
* | | Basic inpainting batch supportAndrii Skaliuk2023-01-282-4/+25
|/ / | | | | | | Modifies batch UI to add optional inpainting support
* / fix broken calls to find_checkpoint_configAUTOMATIC2023-01-272-4/+4
|/
* clarify the option to disable NaN check.AUTOMATIC2023-01-271-0/+2
|
* support detecting midas modelAUTOMATIC2023-01-273-8/+11
| | | | fix broken api for checkpoint list
* remove the need to place configs near modelsAUTOMATIC2023-01-278-134/+242
|
* add an option to enable sections from extras tab in txt2img/img2imgAUTOMATIC2023-01-267-18/+107
| | | | fix some style inconsistenices
* Fix full previews, --no-half-vaebrkirch2023-01-262-5/+5
|
* fix prompt editing break after first batch in img2imgAUTOMATIC2023-01-251-1/+1
|
* add edit_image_conditioning from my earlier edits in case there's an attempt ↵AUTOMATIC2023-01-251-1/+9
| | | | | | to inegrate pix2pix properly this allows to use pix2pix model in img2img though it won't work well this way
* Merge pull request #7197 from mcmonkey4eva/fix-ti-symlinksAUTOMATIC11112023-01-251-1/+1
|\ | | | | allow symlinks in the textual inversion embeddings folder
| * allow symlinks in the textual inversion embeddings folderAlex "mcmonkey" Goodwin2023-01-251-1/+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
|/
* Merge pull request #6510 from brkirch/unet16-upcast-precisionAUTOMATIC11112023-01-259-71/+188
|\ | | | | 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 UNetbrkirch2023-01-257-8/+81
| | | | | | | | 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().
* | 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.
* | | 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/masterAUTOMATIC11112023-01-251-1/+1
|\ \ \ | |_|/ |/| | Adds X/Y/Z Grid Script
| * | handling sub grids and merging into oneEllangoK2023-01-241-1/+1
| | |
* | | 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 ↵AUTOMATIC2023-01-241-2/+9
| | | | | | | | | | | | about it
* | | 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
| | |
* | | add image decod exception handlingVladimir Mandic2023-01-231-1/+5
| |/ |/|
* | 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 Mandic2023-01-234-12/+31
| |\|
| * | improve interrogateVladimir Mandic2023-01-232-12/+18
| | |
* | | add support for apostrophe in extra network namesAUTOMATIC2023-01-231-2/+4
| |/ |/|
* | Merge pull request #7032 from gmq/extra-network-stylesAUTOMATIC11112023-01-232-1/+6
|\ \ | | | | | | Extra network view style
| * | feat(extra-networks): remove view dropdownGuillermo Moreno2023-01-231-11/+9
| | |
| * | feat(extra-networks): add default view settingGuillermo Moreno2023-01-222-4/+8
| | |
| * | feat(extra-networks): add thumbs view styleGuillermo Moreno2023-01-221-9/+12
| | |
* | | api-image-formatVladimir Mandic2023-01-231-10/+24
| | |
* | | a possible fix for broken image upscalingAUTOMATIC2023-01-231-1/+1
| |/ |/|
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-05 16:30:03 +0000