1660 Commits (b6e5edd74657e3fd1fbd04f341b7a84625d4aa7a)

Author SHA1 Message Date
AUTOMATIC1111 01f2ed6844
Merge pull request #5065 from JaySmithWpg/vram-leak
#3449 - VRAM leak when switching to/from inpainting checkpoint
3 years ago
AUTOMATIC1111 151e2cc627
Merge pull request #4461 from brkirch/face-restoration-device-fix
Fix setting device for GFPGAN and CodeFormer
3 years ago
AUTOMATIC1111 cc90dcc933
Merge pull request #4918 from brkirch/pytorch-fixes
Fixes for PyTorch 1.12.1 when using MPS
3 years ago
AUTOMATIC 10923f9b3a calculate dictionary for sampler names only once 3 years ago
AUTOMATIC 40ca34b837 fix for broken sampler selection in img2img and xy plot #4860 #4909 3 years ago
AUTOMATIC 5b2c316890 eliminate duplicated code from #5095 3 years ago
AUTOMATIC1111 997ac57020
Merge pull request #5095 from mlmcgoogan/master
torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly …
3 years ago
AUTOMATIC1111 6df4945718
Merge branch 'master' into DPM++SDE 3 years ago
AUTOMATIC b48b7999c8 Merge remote-tracking branch 'flamelaw/master' 3 years ago
AUTOMATIC b006382784 serve images from where they are saved instead of a temporary directory
add an option to choose a different temporary directory in the UI
add an option to cleanup the selected temporary directory at startup
3 years ago
Matthew McGoogan c67c40f983 torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly set otherwise first. Updating torch_gc() to use the device set by --device-id if specified to avoid OOM edge cases on multi-GPU systems. 3 years ago
MrCheeze 1e506657e1 no-half support for SD 2.0 3 years ago
AUTOMATIC b5050ad207 make SD2 compatible with --medvram setting 3 years ago
flamelaw 755df94b2a set TI AdamW default weight decay to 0 3 years ago
AUTOMATIC 64c7b7975c restore hypernetworks to seemingly working state 3 years ago
AUTOMATIC 1123f52cad add 1024 module for hypernets for the new open clip 3 years ago
AUTOMATIC ce6911158b Add support Stable Diffusion 2.0 3 years ago
Jay Smith c833d5bfaa fixes #3449 - VRAM leak when switching to/from inpainting model 3 years ago
xucj98 263b323de1
Merge branch 'AUTOMATIC1111:master' into draft 3 years ago
Sena fcd75bd874
Fix other apis 3 years ago
Nandaka 904121fecc Support NAI exif for PNG Info 3 years ago
Alex "mcmonkey" Goodwin ffcbbcf385 add filename santization
Probably redundant, considering the model name *is* a filename, but I suppose better safe than sorry.
3 years ago
Alex "mcmonkey" Goodwin 6001684be3 add model_name pattern for saving 3 years ago
flamelaw 1bd57cc979 last_layer_dropout default to False 3 years ago
flamelaw d2c97fc3fe fix dropout, implement train/eval mode 3 years ago
Sena 75b67eebf2
Fix bare base64 not accept 3 years ago
flamelaw 89d8ecff09 small fixes 3 years ago
Tim Patton ac90cf38c6 safetensors optional for now 3 years ago
uservar 0a01f50891
Add DPM++ SDE sampler 3 years ago
Rogerooo c27a973c82 fix null negative_prompt on get requests
Small typo that causes a bug when returning negative prompts from the get request.
3 years ago
Tim Patton 210cb4c128 Use GPU for loading safetensors, disable export 3 years ago
Tim Patton 162fef394f Patch line ui endings 3 years ago
Nicolas Patry 0efffbb407 Supporting `*.safetensors` format.
If a model file exists with extension `.safetensors` then we can load it
more safely than with PyTorch weights.
3 years ago
brkirch 563ea3f6ff Change .cuda() to .to(devices.device) 3 years ago
brkirch e247b7400a Add fixes for PyTorch 1.12.1
Fix typo "MasOS" -> "macOS"

If MPS is available and PyTorch is an earlier version than 1.13:
* Monkey patch torch.Tensor.to to ensure all tensors sent to MPS are contiguous
* Monkey patch torch.nn.functional.layer_norm to ensure input tensor is contiguous (required for this program to work with MPS on unmodified PyTorch 1.12.1)
3 years ago
dtlnor 9ae30b3450 remove cmd args requirement for deepdanbooru 3 years ago
flamelaw 5b57f61ba4 fix pin_memory with different latent sampling method 3 years ago
Tim Patton 637815632f Generalize SD torch load/save to implement safetensor merging compat 3 years ago
AUTOMATIC1111 828438b4a1
Merge pull request #4120 from aliencaocao/enable-override-hypernet
Enable override_settings to take effect for hypernetworks
3 years ago
AUTOMATIC c81d440d87 moved deepdanbooru to pure pytorch implementation 3 years ago
flamelaw 2d22d72cda fix random sampling with pin_memory 3 years ago
flamelaw a4a5735d0a remove unnecessary comment 3 years ago
flamelaw bd68e35de3 Gradient accumulation, autocast fix, new latent sampling method, etc 3 years ago
Tim Patton ac7ecd2d84 Label and load SD .safetensors model files 3 years ago
Keavon Chambers 2f90496b19
Merge branch 'master' into cors-regex 3 years ago
AUTOMATIC 3596af0749 Add API for scripts to add elements anywhere in UI. 3 years ago
AUTOMATIC1111 ccd73fc186
Merge pull request #4717 from papuSpartan/security
Add --server-name to the list of arguments considered insecure
3 years ago
AUTOMATIC1111 41e242b220
Merge pull request #4733 from MaikoTan/api-authorization
feat: add http basic authentication for api
3 years ago
AUTOMATIC 5a6387e189 make it possible to change models etc by editing options using API 3 years ago
Maiko Tan 336c341a7c
Merge branch 'master' into api-authorization 3 years ago
AUTOMATIC1111 84a6f211d4
Merge pull request #4358 from bamarillo/master
[API][Feature] Add Skip endpoint
3 years ago
AUTOMATIC1111 4b22ec4138
Merge pull request #4759 from dtlnor/kill-gradio-progress-bar
Hide Gradio progress again
3 years ago
AUTOMATIC 413c077969 prevent StableDiffusionProcessingImg2Img changing image_mask field as an alternative solution to #4765 3 years ago
AUTOMATIC1111 89daf778fb
Merge pull request #4812 from space-nuko/feature/interrupt-preprocessing
Add interrupt button to preprocessing
3 years ago
AUTOMATIC1111 fe03f9903c
Merge pull request #4819 from killfrenzy96/master
Cleanly undo circular hijack to fix tiling getting stuck on #4818
3 years ago
AUTOMATIC 617c5b486f make it possible for StableDiffusionProcessing to accept multiple different negative prompts in a batch 3 years ago
AUTOMATIC1111 e35d8b493f
Merge pull request #4778 from leppie/fix_unbounded_prompt_growth
Fix unbounded prompt growth/determinism in scripts that loop
3 years ago
AUTOMATIC 0d702930b0 renamed Inpainting strength infotext to Conditional mask weight, made it only appear if using inpainting model, made it possible to read the setting from it using the blue arrow button 3 years ago
AUTOMATIC1111 ff35ae9abb
Merge pull request #4679 from Eugenii10/inpaint-strength-to-infotext
Add 'Inpainting strength' to the 'generation_params' of 'infotext' (params.txt or png chunks)
3 years ago
AUTOMATIC1111 aee611adb8
Merge pull request #4646 from mrauhu/force-update-extensions
Fix: `error: Your local changes to the following files would be overwritten by merge` when trying to update extensions in WSL2 Docker
3 years ago
AUTOMATIC1111 5bfef6e063
Merge pull request #4844 from R-N/vae-misc
Remove no longer necessary code from VAE selector, fix #4651
3 years ago
AUTOMATIC cdc8020d13 change StableDiffusionProcessing to internally use sampler name instead of sampler index 3 years ago
Muhammad Rizqi Nur f1bdf2b15f Merge branch 'a1111' into vae-misc 3 years ago
AUTOMATIC d9fd4525a5 change text for sd_vae_as_default that makes more sense to me 3 years ago
AUTOMATIC1111 3951806058
Merge pull request #4842 from R-N/vae-as-default
Option to use selected VAE as default fallback instead of primary option
3 years ago
Muhammad Rizqi Nur c8f7b5cdd7 Misc
Misc
3 years ago
Muhammad Rizqi Nur 271fd2d700 More verbose messages 3 years ago
Muhammad Rizqi Nur 2c5ca706a7 Remove no longer necessary parts and add vae_file safeguard 3 years ago
Muhammad Rizqi Nur 0663706d44 Option to use selected VAE as default fallback instead of primary option 3 years ago
killfrenzy96 17e4432820 cleanly undo circular hijack #4818 3 years ago
space-nuko c8c40c8a64 Add interrupt button to preprocessing 3 years ago
brkirch a5106a7cdc Remove extra .to(device) 3 years ago
brkirch abfa22c16f Revert "MPS Upscalers Fix"
This reverts commit 768b95394a8500da639b947508f78296524f1836.
3 years ago
Llewellyn Pritchard 9bbe1e3c2e Fix unbounded prompt growth scripts that loop 3 years ago
dtlnor 72b52fbb77 add css override 3 years ago
Maiko Sinkyaet Tan 8f2ff861d3
feat: add http basic authentication for api 3 years ago
papuSpartan 3405acc6a4 Give --server-name priority over --listen and add check for --server-name in addition to --share and --listen 3 years ago
KEV 40ae95d532 Fix retrieving value for 'x/y plot' script. 3 years ago
parasi 9a1aff645a resolve [name] after resolving [filewords] in training 3 years ago
KEV 6fa891b934 Add 'Inpainting strength' to the 'generation_params' dictionary of 'infotext' which is saved into the 'params.txt' or png chunks.
Value appears only if 'Denoising strength' appears too.
3 years ago
Xu Cuijie d20dbe47e0 fix the model name error of Real-ESRGAN in the opts default value 3 years ago
Mrau Hu d671d1d45d Fix: `error: Your local changes to the following files would be overwritten by merge` when run `pull()` method,
because WSL2 Docker set 755 file permissions instead of 644, this results to the error.

Updated `Extension` class: replaced `pull()` with `fetch_and_reset_hard()` method.

Updated `apply_and_restart()` function: replaced `ext.pull()` with `ext.fetch_and_reset_hard()` function.
3 years ago
brkirch f4a488f585 Set device for facelib/facexlib and gfpgan
* FaceXLib/FaceLib doesn't pass the device argument to RetinaFace but instead chooses one itself and sets it to a global - in order to use a device other than its internally chosen default it is necessary to manually replace the default value
* The GFPGAN constructor needs the device argument to work with MPS or a CUDA device ID that differs from the default
3 years ago
AUTOMATIC 98947d173e run installers for newly installed extensions 3 years ago
AUTOMATIC a1a376331c make existing script loading and new preload code use same code for loading modules
limit extension preload scripts to just one file named preload.py
3 years ago
AUTOMATIC1111 e5690d0bf2
Merge pull request #4488 from d8ahazard/ExtensionPreload
Add option to preload extensions
3 years ago
AUTOMATIC 0ab0a50f9a change formatting to match the main program in devices.py 3 years ago
AUTOMATIC c62d17aee3 use the new devices.has_mps() function in register_buffer for DDIM/PLMS fix for OSX 3 years ago
源文雨 1130d5df66
Update devices.py 3 years ago
源文雨 76ab31e188 Fix wrong mps selection below MasOS 12.3 3 years ago
AUTOMATIC 7ba3923d5b move DDIM/PLMS fix for OSX out of the file with inpainting code. 3 years ago
AUTOMATIC1111 bb2e2c82ce
Merge pull request #4233 from thesved/patch-1
Make DDIM and PLMS work on Mac OS
3 years ago
AUTOMATIC1111 b8a2e38758
Merge pull request #4543 from tong-zeng/master
Fix a bug in list_files_with_name
3 years ago
NoCrypt 6165f07e74
Merge branch 'master' into patch-1 3 years ago
AUTOMATIC1111 e666220ee4
Merge pull request #4514 from cluder/4448_fix_ckpt_cache
#4448 fix checkpoint cache usage
3 years ago
AUTOMATIC1111 6a2044f566
Merge pull request #4563 from JingShing/master
Add username and password in ngrok
3 years ago
AUTOMATIC1111 ec95ced6fb
Merge pull request #4573 from liamkerr/4415-update-generation-info
4415 update generation info
3 years ago
AUTOMATIC1111 73776907ec
Merge pull request #4117 from TinkTheBoush/master
Adding optional tag shuffling for training
3 years ago
AUTOMATIC1111 6585cba200
Merge pull request #4395 from snowmeow2/master
Add DeepDanbooru to the interrogate API
3 years ago
KyuSeok Jung a1e271207d
Update dataset.py 3 years ago