3d8256e40c
Merge pull request #6017 from hitomi/master
...
Add memory cache for VAE weights
3 years ago
d81636a091
Merge pull request #6037 from vladmandic/master
...
fix rgba to rgb when using jpeg output
3 years ago
03cb43c3c8
Merge pull request #6133 from vladmandic/memmon-stats
...
add additional memory states
3 years ago
38f5787e67
Merge pull request #6134 from vladmandic/remove-console-message
...
remove unnecessary console message
3 years ago
463048344f
fix shared state dictionary
3 years ago
d3aa2a48e1
remove unnecessary console message
3 years ago
5958bbd244
add additional memory states
3 years ago
5ba04f9ec0
Attempting to solve slow loads for `safetensors`.
...
Fixes #5893
3 years ago
03f486a239
Update shared.py
3 years ago
4df5009acb
Update sd_samplers.py
3 years ago
ae955b0146
fix rgba to rgb when using jpeg output
3 years ago
4af3ca5393
make it so that blank ENSD does not break image generation
3 years ago
893933e05a
Add memory cache for VAE weights
3 years ago
5be9387b23
fix(api): only begin/end state in lock
3 years ago
fa931733f6
fix(api): assign sd_model after settings change
3 years ago
7b7f7e9361
Merge pull request #6003 from eaglgenes101/settings-css-classes
...
Add CSS classes for the settings panels
3 years ago
b12de850ae
Merge pull request #5992 from yuvalabou/F541
...
Fix F541: f-string without any placeholders
3 years ago
a66514e1a3
Merge pull request #6005 from allenbenz/patch-1
...
Fix clip interrogate from the webui
3 years ago
c1512ef9ae
Merge pull request #5999 from vladmandic/trainapi
...
implement train api
3 years ago
8eef9d8e78
a way to add an exception to unpickler without explicitly calling load_with_extra
3 years ago
61a273236f
Fix clip interrogate from the webui
...
A recent change made the image RGBA, which makes the clip interrogator unhappy.
deepbooru and calling the interrogator from the api already do the conversion so this is the only place that needed it.
3 years ago
f60c24f812
Add CSS classes for the settings panels
3 years ago
5f1dfbbc95
implement train api
3 years ago
c5bdba2089
change wording a bit
3 years ago
56e557c6ff
added cheap NN approximation for VAE
3 years ago
3bf5591efe
fix F541 f-string without any placeholders
3 years ago
5927d3fa95
Merge pull request #5977 from philpax/api-dont-save-extras-output
...
fix(api): don't save extras output to disk
3 years ago
a6a54a7529
Merge pull request #5976 from AbstractQbit/fast_preview
...
Add an option for faster low quality previews
3 years ago
0b8acce6a9
separate part of denoiser code into a function to make it easier for extensions to override it
3 years ago
03d7b39453
added an option to filter out deepbooru tags
3 years ago
5a650055de
Removed lenght in sd_model at line 115
...
Commit eba60a4https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5971#issuecomment-1364507379
3 years ago
6247f21a63
fix(api): don't save extras output to disk
3 years ago
11dd79e346
Add an option for faster low quality previews
3 years ago
f23a822f1c
feat(api): include job_timestamp in progress
3 years ago
eba60a42eb
Merge pull request #5627 from deanpress/patch-1
...
fix: fallback model_checkpoint if it's empty
3 years ago
adab48cb1b
Merge pull request #5637 from aednzxy/patch-1
...
API endpoint to refresh checkpoints
3 years ago
8c9e6d3c7d
Merge pull request #5131 from uservar/inpainting-detection
...
Better should_hijack_inpainting detection
3 years ago
064f7b8fd2
Merge pull request #5718 from space-nuko/feature/save-hypernetwork-hash
...
Save hypernetwork hash and fix hypernetwork parameter restoring
3 years ago
c0a8401b5a
rename the option for img2img latent upscale
3 years ago
b2dbd4d698
Merge pull request #5521 from AndrewRyanChama/ryan/img2imglatentscale
...
Add latent upscale option to img2img
3 years ago
34bc3616ec
Merge pull request #5838 from aliencaocao/fix_gradio_pil
...
Dirty fix for missing PIL supported file extensions
3 years ago
ee65237d69
Merge pull request #5747 from yuvalabou/singleton-comparison
...
Format singleton comparisons
3 years ago
7578b50ba6
Merge pull request #5873 from philpax/override-settings-restore-afterwards
...
feat(api): add override_settings_restore_afterwards
3 years ago
fac92610d2
Merge pull request #5753 from calvinballing/master
...
Fix various typos
3 years ago
94450b8877
Merge pull request #5589 from MrCheeze/better-special-model-support
...
Better support for 2.0-inpainting and 2.0-depth special models
3 years ago
9441c28c94
add an option for img2img background color
3 years ago
b81fa1e7f1
Merge pull request #5644 from ThereforeGames/master
...
Improve img2img color correction by performing a luminosity blend
3 years ago
684d7059bc
Merge pull request #5808 from stysmmaker/patch/fix-fnt-size
...
Prevent overlapping in X/Y plot by changing font size
3 years ago
55f3ef876b
Merge pull request #5814 from timntorres/5802-save-upscaler-to-filename
...
Add option to save upscaler to filename suffix in extras tab.
3 years ago
992a877a4a
Merge pull request #4684 from simcop2387/fix-extension-docker
...
Fix docker tmp/ and extensions/ handling for docker.
3 years ago
399b229783
eliminate duplicated code
...
add an option to samplers for skipping next to last sigma
3 years ago
5667ec4ca7
Merge pull request #5797 from mcmonkey4eva/dpm2-a-fix
...
Add a workaround patch for DPM2 a issue
3 years ago
3bfc6c07ae
Merge pull request #5810 from brkirch/fix-training-mps
...
Training fixes for MPS
3 years ago
f0dfed2a17
Merge pull request #5796 from brkirch/invoke-fix
...
Improve InvokeAI cross attention reliability and speed when using MPS for large images
3 years ago
0c747d4013
add a comment for disable xformers hack
3 years ago
13e0295ab6
fix: xformers use importlib
3 years ago
35b1775b32
Use other MPS optimization for large q.shape[0] * q.shape[1]
...
Check if q.shape[0] * q.shape[1] is 2**18 or larger and use the lower memory usage MPS optimization if it is. This should prevent most crashes that were occurring at certain resolutions (e.g. 1024x1024, 2048x512, 512x2048).
Also included is a change to check slice_size and prevent it from being divisible by 4096 which also results in a crash. Otherwise a crash can occur at 1024x512 or 512x1024 resolution.
3 years ago
22f1527fa7
feat(api): add override_settings_restore_afterwards
3 years ago
7ba9bc2fdb
fix dpm2 in img2img as well
3 years ago
c02ef0f428
Fix PIL being imported before its installed (for new users only)
3 years ago
6fd91c9179
Update OptionInfo to match preexisting option.
3 years ago
a7a039d53a
Add option to include upscaler name in filename.
3 years ago
a26fe85056
Add upscaler name as a suffix.
3 years ago
cca16373de
Add attributes used by MPS
3 years ago
16b4509fa6
Add numpy fix for MPS on PyTorch 1.12.1
...
When saving training results with torch.save(), an exception is thrown:
"RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead."
So for MPS, check if Tensor.requires_grad and detach() if necessary.
3 years ago
b7c478c3eb
fix: Modify font size when unable to fit in plot
...
This prevents scenarios where text without line breaks will start overlapping with each other when generating X/Y plots. This is most evident when generating X/Y plots with checkpoints, as most don't contain spaces and sometimes include extra information such as the epoch, making it extra long.
3 years ago
180fdf7809
apply to DPM2 (non-ancestral) as well
3 years ago
8b0703b8fc
Add a workaround patch for DPM2 a issue
...
DPM2 a and DPM2 a Karras samplers are both affected by an issue described by https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3483 and can be resolved by a workaround suggested by the k-diffusion author at https://github.com/crowsonkb/k-diffusion/issues/43#issuecomment-1305195666
3 years ago
35e1017e3e
fix: xformers
3 years ago
c0355caefe
Fix various typos
3 years ago
957e15c464
Correct singleton comparisons
3 years ago
5f407ebd61
Fix comment
3 years ago
1fcb959514
Correctly restore default hypernetwork strength
3 years ago
9d5948e5f7
Correctly restore hypernetwork from hash
3 years ago
7077428209
Save hypernetwork hash in infotext
3 years ago
2e8b5418e3
Improve color correction with luminosity blend
3 years ago
960293d6b2
API endpoint to refresh checkpoints
...
API endpoint to refresh checkpoints
3 years ago
ec0a48826f
unconditionally set use_ema=False if value not specified (True never worked, and all configs except v1-inpainting-inference.yaml already correctly set it to False)
3 years ago
59c6511494
fix: fallback model_checkpoint if it's empty
...
This fixes the following error when SD attempts to start with a deleted checkpoint:
```
Traceback (most recent call last):
File "D:\Web\stable-diffusion-webui\launch.py", line 295, in <module>
start()
File "D:\Web\stable-diffusion-webui\launch.py", line 290, in start
webui.webui()
File "D:\Web\stable-diffusion-webui\webui.py", line 132, in webui
initialize()
File "D:\Web\stable-diffusion-webui\webui.py", line 62, in initialize
modules.sd_models.load_model()
File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 283, in load_model
checkpoint_info = checkpoint_info or select_checkpoint()
File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 117, in select_checkpoint
checkpoint_info = checkpoints_list.get(model_checkpoint, None)
TypeError: unhashable type: 'list'
```
3 years ago
bd81a09eac
fix support for 2.0 inpainting model while maintaining support for 1.5 inpainting model
3 years ago
a1c8ad8828
unload depth model if medvram/lowvram enabled
3 years ago
94a35ca9d6
Merge pull request #5191 from aliencaocao/enable_checkpoint_switching_in_override_settings
...
Support changing checkpoint and vae through override_settings
3 years ago
713c48ddd7
add an 'installed' tag to extensions
3 years ago
991e2dcee9
remove NSFW filter and its dependency; if you still want it, find it in the extensions section
3 years ago
d06592267c
use less javascript for this non-js-only implementation of the clear prompt button.
3 years ago
2028aa06c0
Merge pull request #3198 from papuSpartan/master
...
Add Clear Prompt button to roll_col
3 years ago
89237852f4
Merge pull request #5119 from 0xb8/master
...
Atomically rename saved image to avoid race condition with other processes
3 years ago
cce306cb67
Merge pull request #5441 from timntorres/add-5433-avoid-sending-size-option
...
Add option to avoid sending size between interfaces.
3 years ago
6387043fd2
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
ec5e072124
Merge pull request #4841 from R-N/vae-fix-none
...
Fix None option of VAE selector
3 years ago
bab91b1279
add Noise multiplier option to infotext
3 years ago
8ee1acc1e4
Merge pull request #5373 from mezotaken/master
...
add noise strength parameter similar to NAI
3 years ago
e5e557fa5d
Merge pull request #5404 from szhublox/merger-ram-usage
...
Merger ram usage
3 years ago
505ec7e4d9
cleanup some unneeded imports for hijack files
3 years ago
7dbfd8a7d8
do not replace entire unet for the resolution hack
3 years ago
2641d1b83b
Merge pull request #4978 from aliencaocao/support_any_resolution
...
Patch UNet Forward to support resolutions that are not multiples of 64
3 years ago
4d5fe3bfc0
Merge pull request #5555 from ywx9/master
...
Bug fix (a few lines in modules/api/api.py)
3 years ago
a42a8e9112
Merge pull request #5547 from Ju1-js/master
...
Make "# settings changed" grammatically correct
3 years ago
9539c2045a
Bug fix
3 years ago
ce04ba71b8
Make # settings changed message grammatically correct
...
Make the ": " in the settings changed message not show if 0 settings were changed.
"0 settings changed: ." -> "0 settings changed."
3 years ago
1ed4f0e228
Depth2img model support
3 years ago
358a8628f6
Add latent upscale option to img2img
...
Recently, the option to do latent upscale was added to txt2img highres
fix. This feature runs by scaling the latent sample of the image, and
then running a second pass of img2img.
But, in this edition of highres fix, the image and parameters cannot be
changed between the first pass and second pass. We might want to do a
fixup in img2img before doing the second pass, or might want to run the
second pass at a different resolution.
This change adds the option for img2img to perform its upscale in latent
space, rather than image space, giving very similar results to highres
fix with latent upscale. The result is not exactly the same because
there is an additional latent -> decoder -> image -> encoder -> latent
that won't happen in highres fix, but this conversion has relatively
small losses
3 years ago
965fc5ac5a
delete a file
...
Signed-off-by: zhaohu xing <920232796@qq.com>
3 years ago
5dcc22606d
add hash and fix undo hijack bug
...
Signed-off-by: zhaohu xing <920232796@qq.com>
3 years ago
a25dfebeed
Merge pull request #3 from 920232796/master
...
fix device support for mps
update the support for SD2.0
3 years ago
3ebf977a6e
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
4929503258
fix bugs
...
Signed-off-by: zhaohu xing <920232796@qq.com>
3 years ago
7057c72ae3
Add opt. to avoid sending size between interfaces.
3 years ago
681c450ecd
extras.py: use as little RAM as possible, misc fixes
...
maximum of 2 models loaded at once. delete unneeded model before next
step. fix 'teritary' -> 'tertiary'. gracefully fail when "add
difference" is selected without a tertiary model
3 years ago
44c46f0ed3
make it possible to merge inpainting model with non-inpainting one
3 years ago
8504db5170
fix #4459 breaking inpainting when the option is not specified.
3 years ago
60bd4d52a6
fix incorrect file extension filter for deepdanbooru models
3 years ago
4b0dc206ed
use modelloader for #4956
3 years ago
2a649154ec
Merge pull request #4956 from TiagoSantos81/offline_BLIP
...
[CLIP interrogator] use local file, if available
3 years ago
0d21624cee
move #5216 to the extension
3 years ago
89e1df013b
Merge remote-tracking branch 'wywywywy/autoencoder-hijack'
3 years ago
b6e5edd746
add built-in extension system
...
add support for adding upscalers in extensions
move LDSR, ScuNET and SwinIR to built-in extensions
3 years ago
cf3e844d1d
add noise strength parameter similar to NAI
3 years ago
46b0d230e7
add comment for #4407 and remove seemingly unnecessary cudnn.enabled
3 years ago
2651267e3a
fix #4407 breaking UI entirely for card other than ones related to the PR
3 years ago
681c0003df
Merge pull request #4407 from yoinked-h/patch-1
...
Fix issue with 16xx cards
3 years ago
d2e5b4edfa
Merge pull request #5251 from adieyal/bug/negative-prompt-infotext
...
Fixed incorrect negative prompt text in infotext
3 years ago
c9a2cfdf2a
Merge branch 'master' into racecond_fix
3 years ago
5cd5a672f7
Merge pull request #4459 from kavorite/color-sketch-inpainting
...
add `--gradio-inpaint-tool` and option to specify `color-sketch`
3 years ago
a2feaa95fc
Merge pull request #5194 from brkirch/autocast-and-mps-randn-fixes
...
Use devices.autocast() and fix MPS randn issues
3 years ago
c7af672186
more simple config option name plus mouseover hint for clip skip
3 years ago
c67d8bca4f
Merge pull request #5304 from space-nuko/fix/clip-skip-application
...
Fix clip skip of 1 not being restored from prompts
3 years ago
28c79b8f05
Merge pull request #5328 from jcowens/fix-typo
...
fix typo
3 years ago
eb0b8f92bc
Merge pull request #5331 from smirkingface/openaimodel_fix
...
Fixed AttributeError where openaimodel is not found
3 years ago
bab6ea6b22
Merge pull request #5340 from PhytoEpidemic/master
...
Fix divide by 0 error
3 years ago
b2f17dd367
prevent include_init_images from being passed to StableDiffusionProcessingImg2Img in API #4989
3 years ago
ae81b377d4
Merge pull request #5165 from klimaleksus/fix-sequential-vae
...
Make VAE step sequential to prevent VRAM spikes, will fix #3059 , #2082 , #2561 , #3462
3 years ago
119a945ef7
Fix divide by 0 error
...
Fix of the edge case 0 weight that occasionally will pop up in some specific situations. This was crashing the script.
3 years ago
da698ca92e
Fixed AttributeError where openaimodel is not found
3 years ago
99b19b1a8f
fix typo
3 years ago
e461477869
Fixed safe.py for pytorch 1.13 ckpt files
3 years ago
9c86fb8cac
fix bug
...
Signed-off-by: zhaohu xing <920232796@qq.com>
3 years ago
be2e6de94a
Fix clip skip of 1 not being restored from prompts
3 years ago
0fddb4a1c0
Rework MPS randn fix, add randn_like fix
...
torch.manual_seed() already sets a CPU generator, so there is no reason to create a CPU generator manually. torch.randn_like also needs a MPS fix for k-diffusion, but a torch hijack with randn_like already exists so it can also be used for that.
3 years ago
4d5f1691dd
Use devices.autocast instead of torch.autocast
3 years ago
21effd629d
Add workaround for using MPS with torchsde
3 years ago
a44994e2c9
Fixed incorrect negative prompt text in infotext
...
Previously only the first negative prompt in all_negative_prompts was
being used for infotext. This fixes that by selecting the index-th
negative prompt
3 years ago
3a724e91a2
Change to steps of 8
3 years ago
52cc83d36b
fix bugs
...
Signed-off-by: zhaohu xing <920232796@qq.com>
3 years ago
0831ab476c
Merge branch 'master' into master
3 years ago
7193814cf7
Added purpose of this hijack to comments
3 years ago
36c3613d16
Add autoencoder to sd_hijack
3 years ago
241cbc4d2f
Hijack VQModelInterface back to AutoEncoder
3 years ago
4b3c5bc24b
Merge remote-tracking branch 'pattontim/safetensors'
3 years ago
9a8678f61e
Support changing checkpoint and vae through override_settings
3 years ago
AUTOMATIC1111
Vladimir Mandic
Nicolas Patry
hentailord85ez
hitomi
Philpax
Allen Benz
eaglgenes101
Yuval Aboulafia
linuxmobile ( リナックス )
AbstractQbit
Akiba
brkirch
Alex "mcmonkey" Goodwin
Billy Cao
timntorres
MMaker
Jim Hays
space-nuko
ThereforeGames
Dean Hopkins
MrCheeze
Dean van Dugteren
papuSpartan
ywx9
Ju1-js
Jay Smith
Andrew Ryan
zhaohu xing
Zac Liu
Mackerel
Vladimir Repin
PhytoEpidemic
SmirkingFace
jcowens
Adi Eyal
zhaohu xing
wywywywy