aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
...
| * add more stuff to ignore when creating model from configAUTOMATIC2023-01-103-9/+56
| | | | | | | | prevent .vae.safetensors files from being listed as stable diffusion models
| * disable torch weight initialization and CLIP downloading/reading checkpoint ↵AUTOMATIC2023-01-102-2/+47
| | | | | | | | to speedup creating sd model from config
| * Split history ui.py to ui_progress.pyAUTOMATIC2023-01-102-1924/+9
| |
| * Split history ui.py to ui_progress.pyAndrey2023-01-101-0/+0
| |
| * Split history ui.py to ui_progress.pyAndrey2023-01-101-0/+1928
| |\
| | * Split history ui.py to ui_progress.pyAndrey2023-01-101-0/+0
| | |
| * | Split history ui.py to ui_progress.pyAndrey2023-01-101-0/+0
| |/
| * Variable dropout ratearia1th2023-01-103-28/+81
| | | | | | | | | | | | | | | | | | | | Implements variable dropout rate from #4549 Fixes hypernetwork multiplier being able to modified during training, also fixes user-errors by setting multiplier value to lower values for training. Changes function name to match torch.nn.module standard Fixes RNG reset issue when generating previews by restoring RNG state
| * Merge pull request #6578 from vladmandic/fix-model-loadAUTOMATIC11112023-01-101-5/+10
| |\ | | | | | | allow model load if previous model failed
| | * allow model load if previous model failedVladimir Mandic2023-01-091-5/+10
| | |
| * | relax reponse type check enforcementVladimir Mandic2023-01-101-2/+2
| |/
| * fix broken resolution detection when pasting parameters with old hires fix ↵AUTOMATIC2023-01-091-3/+3
| | | | | | | | enabled
| * Merge pull request #6466 from vladmandic/api-get-memoryAUTOMATIC11112023-01-092-0/+39
| |\ | | | | | | Implement API get-memory
| | * remove bytes -> gb conversionVladimir Mandic2023-01-091-10/+8
| | |
| | * api-get-memoryVladimir Mandic2023-01-072-0/+41
| | |
| * | make a dropdown for prompt template selectionAUTOMATIC2023-01-094-12/+42
| | |
| * | remove/simplify some changes from #6481AUTOMATIC2023-01-093-12/+8
| | |
| * | Merge branch 'master' into varsizeAUTOMATIC11112023-01-0911-101/+233
| |\ \
| | * | Remove fallback for Protocol import and remove Protocol import and remove ↵AUTOMATIC2023-01-091-8/+11
| | | | | | | | | | | | | | | | | | | | | | | | instances of Protocol in code add some whitespace between functions to be in line with other code in the repo
| | * | Merge pull request #6482 from ProGamerGov/patch-6AUTOMATIC11112023-01-091-1/+7
| | |\ \ | | | | | | | | | | Add fallback for Protocol import
| | | * | Add fallback for Protocol importProGamerGov2023-01-071-1/+7
| | | |/
| | * | use existing function for loading VAE weights from fileAUTOMATIC2023-01-091-8/+5
| | | |
| | * | Merge pull request #6528 from PlasmaPower/vae-safetensorsAUTOMATIC11112023-01-091-3/+18
| | |\ \ | | | | | | | | | | Add support for loading VAEs from safetensors files
| | | * | Add support for loading VAEs from safetensor filesLee Bousfield2023-01-081-3/+18
| | | | |
| | * | | add an option to use old hiresfix width/height behaviorAUTOMATIC2023-01-094-17/+50
| | |/ / | | | | | | | | | | | | add a visual effect to inactive hires fix elements
| | * | Merge pull request #6465 from brkirch/fix-trainingAUTOMATIC11112023-01-081-2/+2
| | |\ \ | | | | | | | | | | Fix training for newer PyTorch builds
| | | * | In-place operations can break gradient calculationbrkirch2023-01-071-2/+2
| | | |/
| | * | remove some code duplicationAUTOMATIC2023-01-081-17/+16
| | | | | | | | | | | | | | | | | | | | remove calls to locals() add a test for img2img with script
| | * | Merge pull request #6469 from noodleanon/scripts-from-apiAUTOMATIC11112023-01-083-9/+46
| | |\ \ | | | | | | | | | | Run scripts from API
| | | * | Corrected is_img2img paramnoodleanon2023-01-081-1/+1
| | | | |
| | | * | Added script support in txt2img endpointnoodleanon2023-01-072-4/+20
| | | | |
| | | * | Merge branch 'AUTOMATIC1111:master' into img2img-api-scriptsnoodleanon2023-01-0717-265/+755
| | | |\|
| | | * | allow img2img api to run scriptsnoodleanon2023-01-053-6/+27
| | | | |
| | * | | make it possible for extensions/scripts to add their own embedding directoriesAUTOMATIC2023-01-082-69/+108
| | | | |
| | * | | skip images in embeddings dir if they have a second .preview extensionAUTOMATIC2023-01-081-0/+4
| | | |/ | | |/|
| * | | Move batchsize checkdan2023-01-072-3/+3
| | | |
| * | | Add checkbox for variable training dimsdan2023-01-074-5/+8
| | | |
| * | | Allow variable img sizedan2023-01-072-9/+13
| |/ /
| * | add "from" resolution for hires fix to be less confusing.AUTOMATIC2023-01-071-1/+1
| | |
| * | Merge pull request #6448 from aednzxy/patch-2AUTOMATIC11112023-01-071-1/+1
| |\ \ | | | | | | | | increase upscale api validation limit
| | * | increase upscale api validation limitDean Hopkins2023-01-061-1/+1
| | | |
| * | | Merge pull request #6055 from brkirch/sub-quad_attn_optAUTOMATIC11112023-01-074-37/+318
| |\ \ \ | | | | | | | | | | Add Birch-san's sub-quadratic attention implementation
| | * | | Added licensebrkirch2023-01-062-1/+2
| | | | |
| | * | | Allow Doggettx's cross attention opt without CUDAbrkirch2023-01-061-1/+1
| | | | |
| | * | | Change sub-quad chunk threshold to use percentagebrkirch2023-01-062-10/+10
| | | | |
| | * | | Use narrow instead of dynamic_slicebrkirch2023-01-061-15/+19
| | | | |
| | * | | Merge remote-tracking branch 'upstream/master' into sub-quad_attn_optbrkirch2023-01-0617-135/+390
| | |\ \ \
| | * \ \ \ Merge branch 'AUTOMATIC1111:master' into sub-quad_attn_optbrkirch2023-01-0626-629/+871
| | |\ \ \ \
| | * | | | | Add Birch-san's sub-quadratic attention implementationbrkirch2023-01-064-34/+310
| | | | | | |
| * | | | | | rework hires fix preview for #6437: movie it to where it takes less place, ↵AUTOMATIC2023-01-073-14/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | make it actually account for all relevant sliders and calculate dimensions correctly
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-06 03:37:57 +0000