fd4461d44c
Merge pull request #6196 from philpax/add-embeddings-api
...
feat(api): add /sdapi/v1/embeddings
2023-01-02 06:11:10 +03:00
f39a79d143
Merge pull request #6183 from Kryptortio/add_more_element_ids
...
Add additional elem_id/HTML ids
2023-01-02 06:10:26 +03:00
c65909ad16
feat(api): return more data for embeddings
2023-01-02 12:21:48 +11:00
b5819d9bf1
feat(api): add /sdapi/v1/embeddings
2023-01-02 10:18:11 +11:00
311354c0bb
fix the issue with training on SD2.0
2023-01-02 00:38:09 +03:00
a005fccddd
Add a lot more elem_id/HTML id, modified some that were duplicates for seed section
2023-01-01 20:06:52 +01:00
e672cfb074
rework of callback for #6094
2023-01-01 18:37:55 +03:00
6062c85d4d
Merge pull request #6094 from AlUlkesh/master
...
Adding image numbers on grids
2023-01-01 18:31:01 +03:00
524d532b38
moved roll artist to built-in extensions
2023-01-01 14:07:40 +03:00
5f12b23b8b
Adding image numbers on grids
...
New grid option in settings enables adding of image numbers on grids. This makes identifying the images, especially in larger batches, much easier.
Revert "Adding image numbers on grids"
This reverts commit 3530c283b4b1d3a3cab40efbffe4cf2697938b6f.
Implements Callback for image grid loop
Necessary to make "Add image's number to its picture in the grid" extension possible.
2023-01-01 11:21:50 +01:00
e5f1a37cb9
make refresh buttons look more nice
2023-01-01 13:08:40 +03:00
b46b97fa29
more fixes for gradio update
2023-01-01 11:38:17 +03:00
76f256fe8f
Bump gradio version #YOLO
2023-01-01 11:08:39 +03:00
11d432d92d
add refresh buttons to checkpoint merger
2023-01-01 10:35:38 +03:00
16b9661d27
change karras scheduler sigmas to values recommended by SD from old 0.1 to 10 with an option to revert to old
2023-01-01 09:51:37 +03:00
210449b374
fix 'RuntimeError: Expected all tensors to be on the same device' error preventing models from loading on lowvram/medvram.
2023-01-01 02:41:15 +03:00
29a3a7eb13
show sampler selection in dropdown, add option selection to revert to old radio group
2023-01-01 01:19:10 +03:00
360feed9b5
HAPPY NEW YEAR
...
make save to zip into its own button instead of a checkbox
2023-01-01 00:38:58 +03:00
f4535f6e4f
make it so that memory/embeddings info is displayed in a separate UI element from generation parameters, and is preserved when you change the displayed infotext by clicking on gallery images
2022-12-31 23:40:55 +03:00
bdbe09827b
changed embedding accepted shape detection to use existing code and support the new alt-diffusion model, and reformatted messages a bit #6149
2022-12-31 22:49:09 +03:00
c24a314c5e
Merge pull request #6149 from vladmandic/validate-embeddings
...
validate textual inversion embeddings
2022-12-31 22:33:12 +03:00
f378b8d53a
Merge pull request #6143 from vladmandic/fix-interrogate
...
fix interrogate
2022-12-31 22:20:56 +03:00
f55ac33d44
validate textual inversion embeddings
2022-12-31 11:27:02 -05:00
f34c734172
alt-diffusion integration
2022-12-31 18:06:35 +03:00
65be1df7bb
initialize result so not to cause exception on empty results
2022-12-31 07:46:04 -05:00
3f401cdb64
Merge remote-tracking branch 'baai-open-internal/master' into alt-diffusion
2022-12-31 13:02:28 +03:00
fef98723b2
set sd_model for API later, inside the lock, to prevent multiple requests with different models ending up with incorrect results #5877 #6012
2022-12-31 12:44:26 +03:00
26522c7dc8
Merge pull request #6015 from philpax/api-begin-end-in-queue
...
fix(api): only begin/end state in lock
2022-12-31 12:23:39 +03:00
3d8256e40c
Merge pull request #6017 from hitomi/master
...
Add memory cache for VAE weights
2022-12-31 12:22:59 +03:00
d81636a091
Merge pull request #6037 from vladmandic/master
...
fix rgba to rgb when using jpeg output
2022-12-31 12:14:41 +03:00
03cb43c3c8
Merge pull request #6133 from vladmandic/memmon-stats
...
add additional memory states
2022-12-31 10:52:58 +03:00
38f5787e67
Merge pull request #6134 from vladmandic/remove-console-message
...
remove unnecessary console message
2022-12-31 10:52:30 +03:00
463048344f
fix shared state dictionary
2022-12-30 19:41:47 -05:00
d3aa2a48e1
remove unnecessary console message
2022-12-30 19:38:53 -05:00
5958bbd244
add additional memory states
2022-12-30 19:36:36 -05:00
5ba04f9ec0
Attempting to solve slow loads for `safetensors`.
...
Fixes #5893
2022-12-27 11:27:19 +01:00
03f486a239
Update shared.py
2022-12-26 20:49:33 +00:00
4df5009acb
Update sd_samplers.py
2022-12-26 20:49:13 +00:00
ae955b0146
fix rgba to rgb when using jpeg output
2022-12-26 09:56:19 -05:00
4af3ca5393
make it so that blank ENSD does not break image generation
2022-12-26 10:11:28 +03:00
893933e05a
Add memory cache for VAE weights
2022-12-25 20:49:25 +08:00
5be9387b23
fix(api): only begin/end state in lock
2022-12-25 21:45:44 +11:00
fa931733f6
fix(api): assign sd_model after settings change
2022-12-25 20:17:49 +11:00
7b7f7e9361
Merge pull request #6003 from eaglgenes101/settings-css-classes
...
Add CSS classes for the settings panels
2022-12-25 09:17:34 +03:00
b12de850ae
Merge pull request #5992 from yuvalabou/F541
...
Fix F541: f-string without any placeholders
2022-12-25 09:16:08 +03:00
a66514e1a3
Merge pull request #6005 from allenbenz/patch-1
...
Fix clip interrogate from the webui
2022-12-25 09:12:29 +03:00
c1512ef9ae
Merge pull request #5999 from vladmandic/trainapi
...
implement train api
2022-12-25 09:11:42 +03:00
8eef9d8e78
a way to add an exception to unpickler without explicitly calling load_with_extra
2022-12-25 09:03:56 +03:00
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.
2022-12-24 20:23:12 -08:00
f60c24f812
Add CSS classes for the settings panels
2022-12-24 22:16:01 -05:00
5f1dfbbc95
implement train api
2022-12-24 18:02:22 -05:00
c5bdba2089
change wording a bit
2022-12-24 22:41:35 +03:00
56e557c6ff
added cheap NN approximation for VAE
2022-12-24 22:39:10 +03:00
3bf5591efe
fix F541 f-string without any placeholders
2022-12-24 21:35:29 +02:00
5927d3fa95
Merge pull request #5977 from philpax/api-dont-save-extras-output
...
fix(api): don't save extras output to disk
2022-12-24 18:50:45 +03:00
a6a54a7529
Merge pull request #5976 from AbstractQbit/fast_preview
...
Add an option for faster low quality previews
2022-12-24 18:38:42 +03:00
0b8acce6a9
separate part of denoiser code into a function to make it easier for extensions to override it
2022-12-24 18:38:16 +03:00
03d7b39453
added an option to filter out deepbooru tags
2022-12-24 16:22:47 +03:00
5a650055de
Removed lenght in sd_model at line 115
...
Commit eba60a4https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5971#issuecomment-1364507379
2022-12-24 09:25:35 -03:00
6247f21a63
fix(api): don't save extras output to disk
2022-12-24 22:04:53 +11:00
11dd79e346
Add an option for faster low quality previews
2022-12-24 14:00:17 +03:00
f23a822f1c
feat(api): include job_timestamp in progress
2022-12-24 20:45:16 +11:00
eba60a42eb
Merge pull request #5627 from deanpress/patch-1
...
fix: fallback model_checkpoint if it's empty
2022-12-24 12:20:31 +03:00
adab48cb1b
Merge pull request #5637 from aednzxy/patch-1
...
API endpoint to refresh checkpoints
2022-12-24 12:19:43 +03:00
8c9e6d3c7d
Merge pull request #5131 from uservar/inpainting-detection
...
Better should_hijack_inpainting detection
2022-12-24 12:19:06 +03:00
064f7b8fd2
Merge pull request #5718 from space-nuko/feature/save-hypernetwork-hash
...
Save hypernetwork hash and fix hypernetwork parameter restoring
2022-12-24 11:14:19 +03:00
c0a8401b5a
rename the option for img2img latent upscale
2022-12-24 11:12:17 +03:00
b2dbd4d698
Merge pull request #5521 from AndrewRyanChama/ryan/img2imglatentscale
...
Add latent upscale option to img2img
2022-12-24 11:10:35 +03:00
34bc3616ec
Merge pull request #5838 from aliencaocao/fix_gradio_pil
...
Dirty fix for missing PIL supported file extensions
2022-12-24 10:24:33 +03:00
ee65237d69
Merge pull request #5747 from yuvalabou/singleton-comparison
...
Format singleton comparisons
2022-12-24 10:17:38 +03:00
7578b50ba6
Merge pull request #5873 from philpax/override-settings-restore-afterwards
...
feat(api): add override_settings_restore_afterwards
2022-12-24 10:15:04 +03:00
fac92610d2
Merge pull request #5753 from calvinballing/master
...
Fix various typos
2022-12-24 09:58:28 +03:00
94450b8877
Merge pull request #5589 from MrCheeze/better-special-model-support
...
Better support for 2.0-inpainting and 2.0-depth special models
2022-12-24 09:53:44 +03:00
9441c28c94
add an option for img2img background color
2022-12-24 09:46:35 +03:00
b81fa1e7f1
Merge pull request #5644 from ThereforeGames/master
...
Improve img2img color correction by performing a luminosity blend
2022-12-24 09:17:40 +03:00
684d7059bc
Merge pull request #5808 from stysmmaker/patch/fix-fnt-size
...
Prevent overlapping in X/Y plot by changing font size
2022-12-24 09:13:05 +03:00
55f3ef876b
Merge pull request #5814 from timntorres/5802-save-upscaler-to-filename
...
Add option to save upscaler to filename suffix in extras tab.
2022-12-24 09:07:00 +03:00
992a877a4a
Merge pull request #4684 from simcop2387/fix-extension-docker
...
Fix docker tmp/ and extensions/ handling for docker.
2022-12-24 09:06:10 +03:00
399b229783
eliminate duplicated code
...
add an option to samplers for skipping next to last sigma
2022-12-24 09:03:45 +03:00
5667ec4ca7
Merge pull request #5797 from mcmonkey4eva/dpm2-a-fix
...
Add a workaround patch for DPM2 a issue
2022-12-24 08:51:43 +03:00
3bfc6c07ae
Merge pull request #5810 from brkirch/fix-training-mps
...
Training fixes for MPS
2022-12-24 08:34:46 +03:00
f0dfed2a17
Merge pull request #5796 from brkirch/invoke-fix
...
Improve InvokeAI cross attention reliability and speed when using MPS for large images
2022-12-24 08:21:19 +03:00
0c747d4013
add a comment for disable xformers hack
2022-12-24 07:57:56 +03:00
13e0295ab6
fix: xformers use importlib
2022-12-24 11:17:21 +08:00
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.
2022-12-20 21:30:00 -05:00
22f1527fa7
feat(api): add override_settings_restore_afterwards
2022-12-20 20:36:49 +11:00
7ba9bc2fdb
fix dpm2 in img2img as well
2022-12-18 19:16:42 -08:00
c02ef0f428
Fix PIL being imported before its installed (for new users only)
2022-12-18 20:51:59 +08:00
6fd91c9179
Update OptionInfo to match preexisting option.
2022-12-17 08:59:02 -08:00
a7a039d53a
Add option to include upscaler name in filename.
2022-12-17 08:50:20 -08:00
a26fe85056
Add upscaler name as a suffix.
2022-12-17 05:11:06 -08:00
cca16373de
Add attributes used by MPS
2022-12-17 04:23:08 -05:00
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.
2022-12-17 04:22:58 -05:00
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.
2022-12-17 00:45:43 -05:00
180fdf7809
apply to DPM2 (non-ancestral) as well
2022-12-16 08:42:00 -08:00
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
2022-12-16 08:18:29 -08:00
35e1017e3e
fix: xformers
2022-12-16 20:43:09 +08:00
c0355caefe
Fix various typos
2022-12-14 21:01:32 -05:00
957e15c464
Correct singleton comparisons
2022-12-14 20:59:33 +02:00
5f407ebd61
Fix comment
2022-12-13 14:32:26 -08:00
1fcb959514
Correctly restore default hypernetwork strength
2022-12-13 14:30:54 -08:00
9d5948e5f7
Correctly restore hypernetwork from hash
2022-12-13 14:25:16 -08:00
7077428209
Save hypernetwork hash in infotext
2022-12-13 13:05:40 -08:00
2e8b5418e3
Improve color correction with luminosity blend
2022-12-11 18:03:36 -05:00
960293d6b2
API endpoint to refresh checkpoints
...
API endpoint to refresh checkpoints
2022-12-11 19:16:44 +00:00
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)
2022-12-11 11:18:34 -05:00
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'
```
2022-12-11 17:08:51 +01:00
bd81a09eac
fix support for 2.0 inpainting model while maintaining support for 1.5 inpainting model
2022-12-10 11:29:26 -05:00
a1c8ad8828
unload depth model if medvram/lowvram enabled
2022-12-10 11:02:47 -05:00
94a35ca9d6
Merge pull request #5191 from aliencaocao/enable_checkpoint_switching_in_override_settings
...
Support changing checkpoint and vae through override_settings
2022-12-10 16:29:40 +03:00
713c48ddd7
add an 'installed' tag to extensions
2022-12-10 15:05:22 +03:00
991e2dcee9
remove NSFW filter and its dependency; if you still want it, find it in the extensions section
2022-12-10 14:54:16 +03:00
d06592267c
use less javascript for this non-js-only implementation of the clear prompt button.
2022-12-10 13:46:18 +03:00
2028aa06c0
Merge pull request #3198 from papuSpartan/master
...
Add Clear Prompt button to roll_col
2022-12-10 13:35:51 +03:00
89237852f4
Merge pull request #5119 from 0xb8/master
...
Atomically rename saved image to avoid race condition with other processes
2022-12-10 13:26:07 +03:00
cce306cb67
Merge pull request #5441 from timntorres/add-5433-avoid-sending-size-option
...
Add option to avoid sending size between interfaces.
2022-12-10 11:07:16 +03:00
6387043fd2
Merge branch 'AUTOMATIC1111:master' into master
2022-12-10 00:02:39 -08:00
ec5e072124
Merge pull request #4841 from R-N/vae-fix-none
...
Fix None option of VAE selector
2022-12-10 09:58:20 +03:00
bab91b1279
add Noise multiplier option to infotext
2022-12-10 09:51:26 +03:00
8ee1acc1e4
Merge pull request #5373 from mezotaken/master
...
add noise strength parameter similar to NAI
2022-12-10 09:36:24 +03:00
e5e557fa5d
Merge pull request #5404 from szhublox/merger-ram-usage
...
Merger ram usage
2022-12-10 09:33:39 +03:00
505ec7e4d9
cleanup some unneeded imports for hijack files
2022-12-10 09:17:39 +03:00
7dbfd8a7d8
do not replace entire unet for the resolution hack
2022-12-10 09:14:45 +03:00
2641d1b83b
Merge pull request #4978 from aliencaocao/support_any_resolution
...
Patch UNet Forward to support resolutions that are not multiples of 64
2022-12-10 08:45:41 +03:00
4d5fe3bfc0
Merge pull request #5555 from ywx9/master
...
Bug fix (a few lines in modules/api/api.py)
2022-12-10 08:27:44 +03:00
a42a8e9112
Merge pull request #5547 from Ju1-js/master
...
Make "# settings changed" grammatically correct
2022-12-10 08:20:22 +03:00
9539c2045a
Bug fix
2022-12-09 23:03:06 +09:00
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."
2022-12-08 22:47:45 -08:00
1ed4f0e228
Depth2img model support
2022-12-08 20:50:08 -06:00
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
2022-12-08 07:09:09 +00:00
965fc5ac5a
delete a file
...
Signed-off-by: zhaohu xing <920232796@qq.com>
2022-12-06 16:15:15 +08:00
5dcc22606d
add hash and fix undo hijack bug
...
Signed-off-by: zhaohu xing <920232796@qq.com>
2022-12-06 16:04:50 +08:00
a25dfebeed
Merge pull request #3 from 920232796/master
...
fix device support for mps
update the support for SD2.0
2022-12-06 09:17:57 +08:00
3ebf977a6e
Merge branch 'AUTOMATIC1111:master' into master
2022-12-06 09:16:15 +08:00
4929503258
fix bugs
...
Signed-off-by: zhaohu xing <920232796@qq.com>
2022-12-06 09:03:55 +08:00
7057c72ae3
Add opt. to avoid sending size between interfaces.
2022-12-05 03:41:36 -08:00
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
2022-12-04 10:31:06 -05:00
44c46f0ed3
make it possible to merge inpainting model with non-inpainting one
2022-12-04 12:30:44 +03:00
8504db5170
fix #4459 breaking inpainting when the option is not specified.
2022-12-04 01:04:24 +03:00
60bd4d52a6
fix incorrect file extension filter for deepdanbooru models
2022-12-03 18:46:09 +03:00
4b0dc206ed
use modelloader for #4956
2022-12-03 18:45:51 +03:00
2a649154ec
Merge pull request #4956 from TiagoSantos81/offline_BLIP
...
[CLIP interrogator] use local file, if available
2022-12-03 18:17:56 +03:00
0d21624cee
move #5216 to the extension
2022-12-03 18:16:19 +03:00
89e1df013b
Merge remote-tracking branch 'wywywywy/autoencoder-hijack'
2022-12-03 18:08:10 +03:00
b6e5edd746
add built-in extension system
...
add support for adding upscalers in extensions
move LDSR, ScuNET and SwinIR to built-in extensions
2022-12-03 18:06:33 +03:00
cf3e844d1d
add noise strength parameter similar to NAI
2022-12-03 18:05:47 +03:00
46b0d230e7
add comment for #4407 and remove seemingly unnecessary cudnn.enabled
2022-12-03 16:01:23 +03:00
2651267e3a
fix #4407 breaking UI entirely for card other than ones related to the PR
2022-12-03 15:57:52 +03:00
681c0003df
Merge pull request #4407 from yoinked-h/patch-1
...
Fix issue with 16xx cards
2022-12-03 10:30:34 +03:00
d2e5b4edfa
Merge pull request #5251 from adieyal/bug/negative-prompt-infotext
...
Fixed incorrect negative prompt text in infotext
2022-12-03 10:21:43 +03:00
c9a2cfdf2a
Merge branch 'master' into racecond_fix
2022-12-03 10:19:51 +03:00
5cd5a672f7
Merge pull request #4459 from kavorite/color-sketch-inpainting
...
add `--gradio-inpaint-tool` and option to specify `color-sketch`
2022-12-03 10:06:27 +03:00
a2feaa95fc
Merge pull request #5194 from brkirch/autocast-and-mps-randn-fixes
...
Use devices.autocast() and fix MPS randn issues
2022-12-03 09:58:08 +03:00
c7af672186
more simple config option name plus mouseover hint for clip skip
2022-12-03 09:41:39 +03:00
c67d8bca4f
Merge pull request #5304 from space-nuko/fix/clip-skip-application
...
Fix clip skip of 1 not being restored from prompts
2022-12-03 09:37:10 +03:00
28c79b8f05
Merge pull request #5328 from jcowens/fix-typo
...
fix typo
2022-12-03 09:20:39 +03:00
eb0b8f92bc
Merge pull request #5331 from smirkingface/openaimodel_fix
...
Fixed AttributeError where openaimodel is not found
2022-12-03 09:18:36 +03:00
bab6ea6b22
Merge pull request #5340 from PhytoEpidemic/master
...
Fix divide by 0 error
2022-12-03 09:17:54 +03:00
b2f17dd367
prevent include_init_images from being passed to StableDiffusionProcessingImg2Img in API #4989
2022-12-03 09:15:24 +03:00
ae81b377d4
Merge pull request #5165 from klimaleksus/fix-sequential-vae
...
Make VAE step sequential to prevent VRAM spikes, will fix #3059 , #2082 , #2561 , #3462
2022-12-03 08:29:56 +03:00
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.
2022-12-02 12:16:29 -06:00
da698ca92e
Fixed AttributeError where openaimodel is not found
2022-12-02 13:47:02 +01:00
99b19b1a8f
fix typo
2022-12-02 02:53:26 -08:00
e461477869
Fixed safe.py for pytorch 1.13 ckpt files
2022-12-02 11:12:13 +01:00
9c86fb8cac
fix bug
...
Signed-off-by: zhaohu xing <920232796@qq.com>
2022-12-02 16:08:46 +08:00
be2e6de94a
Fix clip skip of 1 not being restored from prompts
2022-12-01 11:34:16 -08:00
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.
2022-11-30 10:33:42 -05:00
4d5f1691dd
Use devices.autocast instead of torch.autocast
2022-11-30 10:33:42 -05:00
21effd629d
Add workaround for using MPS with torchsde
2022-11-30 10:33:39 -05:00
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
2022-11-30 15:23:53 +02:00
3a724e91a2
Change to steps of 8
2022-11-30 20:52:32 +08:00
52cc83d36b
fix bugs
...
Signed-off-by: zhaohu xing <920232796@qq.com>
2022-11-30 14:56:12 +08:00
0831ab476c
Merge branch 'master' into master
2022-11-30 10:13:17 +08:00
7193814cf7
Added purpose of this hijack to comments
2022-11-29 19:22:53 +00:00
36c3613d16
Add autoencoder to sd_hijack
2022-11-29 17:40:02 +00:00
241cbc4d2f
Hijack VQModelInterface back to AutoEncoder
2022-11-29 17:38:16 +00:00
4b3c5bc24b
Merge remote-tracking branch 'pattontim/safetensors'
2022-11-29 17:06:15 +03:00
9a8678f61e
Support changing checkpoint and vae through override_settings
2022-11-29 11:11:29 +08:00
75c4511e6b
add AltDiffusion to webui
...
Signed-off-by: zhaohu xing <920232796@qq.com>
2022-11-29 10:28:41 +08:00
98ca437edf
Refactor and instead check if mps is being used, not availability
2022-11-28 21:18:51 -05:00
67efee33a6
Make VAE step sequential to prevent VRAM spikes
2022-11-28 16:29:43 +05:00
0b5dcb3d7c
fix an error that happens when you type into prompt while switching model, put queue stuff into separate file
2022-11-28 09:00:10 +03:00
0376da180c
make it possible to save nai model using safetensors
2022-11-28 08:39:59 +03:00
bb11bee22a
if image on disk was deleted between being generated and request being completed, do use temporary dir to store it for the browser
2022-11-27 23:14:13 +03:00
aa12dfada0
fix the bug that makes it impossible to send images to other tabs
2022-11-27 23:04:42 +03:00
39827a3998
Merge pull request #4688 from parasi22/resolve-embedding-name-in-filewords
...
resolve [name] after resolving [filewords] in training
2022-11-27 22:46:49 +03:00
9146a5884c
Better should hijack inpainting detection
2022-11-27 19:11:50 +00:00
9e78d2c419
Merge pull request #4416 from Keavon/cors-regex
...
Add CORS-allow policy launch argument using regex
2022-11-27 18:50:12 +03:00
ef567b083c
Merge pull request #4919 from brkirch/deepbooru-fix
...
Fix support for devices other than CUDA in DeepBooru
2022-11-27 16:59:22 +03:00
554787231a
Merge pull request #5117 from aliencaocao/fix_api_sampler_name
...
Fix api ignoring sampler_name settings
2022-11-27 16:51:47 +03:00
b24aed0b69
Merge pull request #4960 from Hugo-Matias/master
...
fix null negative_prompt on get requests
2022-11-27 16:36:29 +03:00
8c13f3a2a5
cherrypick from #4971
2022-11-27 16:35:35 +03:00
c33b9a6da7
Merge pull request #4583 from NoCrypt/patch-1
...
Forcing HTTPS instead of HTTP for ngrok
2022-11-27 16:30:23 +03:00
506d529d19
rework #5012 to also work for pictures dragged into the prompt and also add Clip skip + ENSD to parameters
2022-11-27 16:28:32 +03:00
185ab3cbd1
Atomically rename saved image to avoid race condition with other processes.
2022-11-27 18:23:08 +05:00
06ada734c7
Prevent warning on sampler_index if sampler_name is being used
2022-11-27 21:19:47 +08:00
3cf93de24f
Fix sampler_name for API requests are being ignored
2022-11-27 21:12:37 +08:00
488f831d52
Merge pull request #5012 from Nandaka/master
...
Support NAI style exif in PNG Info for Send... buttons
2022-11-27 15:57:50 +03:00
9ec0a41a58
Merge pull request #4977 from sena-nana/master
...
Fix API img2img not accepting bare base64 strings
2022-11-27 15:54:39 +03:00
dac9b6f15d
add safetensors support for model merging #4869
2022-11-27 15:51:29 +03:00
6074175faa
add safetensors to requirements
2022-11-27 14:46:40 +03:00
f108782e30
Merge pull request #4930 from Narsil/allow_to_load_safetensors_file
...
Supporting `*.safetensors` format.
2022-11-27 14:36:55 +03:00
a89d7f4f38
Merge pull request #4913 from dtlnor/deprecated-deepdanbooru-patch
...
Remove cmd args requirement for deepdanbooru
2022-11-27 14:19:32 +03:00
eb08550108
Merge pull request #4663 from xucj98/draft
...
fix the model name error of Real-ESRGAN in the opts default value
2022-11-27 14:16:45 +03:00
ca8c764af8
Merge pull request #4986 from mcmonkey4eva/add-model-name
...
add model_name pattern for saving
2022-11-27 13:58:34 +03:00
8de897b3da
Merge pull request #5085 from MrCheeze/sd-2.0-automatic-2
...
no-half support for SD 2.0
2022-11-27 13:54:08 +03:00
01f2ed6844
Merge pull request #5065 from JaySmithWpg/vram-leak
...
#3449 - VRAM leak when switching to/from inpainting checkpoint
2022-11-27 13:52:14 +03:00
151e2cc627
Merge pull request #4461 from brkirch/face-restoration-device-fix
...
Fix setting device for GFPGAN and CodeFormer
2022-11-27 13:48:25 +03:00
cc90dcc933
Merge pull request #4918 from brkirch/pytorch-fixes
...
Fixes for PyTorch 1.12.1 when using MPS
2022-11-27 13:47:01 +03:00
10923f9b3a
calculate dictionary for sampler names only once
2022-11-27 13:43:10 +03:00
40ca34b837
fix for broken sampler selection in img2img and xy plot #4860 #4909
2022-11-27 13:17:39 +03:00
5b2c316890
eliminate duplicated code from #5095
2022-11-27 13:08:54 +03:00
997ac57020
Merge pull request #5095 from mlmcgoogan/master
...
torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly …
2022-11-27 12:56:02 +03:00
6df4945718
Merge branch 'master' into DPM++SDE
2022-11-27 12:54:45 +03:00
b48b7999c8
Merge remote-tracking branch 'flamelaw/master'
2022-11-27 12:19:59 +03:00
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
2022-11-27 11:52:53 +03:00
349f0461ec
Merge branch 'master' into support_any_resolution
2022-11-27 12:39:31 +08:00
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.
2022-11-26 23:25:16 +00:00
1e506657e1
no-half support for SD 2.0
2022-11-26 13:28:44 -05:00
b5050ad207
make SD2 compatible with --medvram setting
2022-11-26 20:52:16 +03:00
755df94b2a
set TI AdamW default weight decay to 0
2022-11-27 00:35:44 +09:00
64c7b7975c
restore hypernetworks to seemingly working state
2022-11-26 16:45:57 +03:00
1123f52cad
add 1024 module for hypernets for the new open clip
2022-11-26 16:37:37 +03:00
ce6911158b
Add support Stable Diffusion 2.0
2022-11-26 16:10:46 +03:00
c833d5bfaa
fixes #3449 - VRAM leak when switching to/from inpainting model
2022-11-25 20:15:11 -06:00
263b323de1
Merge branch 'AUTOMATIC1111:master' into draft
2022-11-25 17:07:00 +08:00
a2ae5a6555
[interrogator] mkdir check
2022-11-24 13:04:45 +00:00
fcd75bd874
Fix other apis
2022-11-24 13:10:40 +08:00
904121fecc
Support NAI exif for PNG Info
2022-11-24 02:39:09 +00:00
ffcbbcf385
add filename santization
...
Probably redundant, considering the model name *is* a filename, but I suppose better safe than sorry.
2022-11-23 06:44:20 -08:00
6001684be3
add model_name pattern for saving
2022-11-23 06:35:44 -08:00
1bd57cc979
last_layer_dropout default to False
2022-11-23 20:21:52 +09:00
d2c97fc3fe
fix dropout, implement train/eval mode
2022-11-23 20:00:00 +09:00
adb6cb7619
Patch UNet Forward to support resolutions that are not multiples of 64
...
Also modifed the UI to no longer step in 64
2022-11-23 18:11:24 +08:00
75b67eebf2
Fix bare base64 not accept
2022-11-23 17:43:58 +08:00
89d8ecff09
small fixes
2022-11-23 02:49:01 +09:00
ac90cf38c6
safetensors optional for now
2022-11-22 10:13:07 -05:00
0a01f50891
Add DPM++ SDE sampler
2022-11-22 14:24:50 +00:00
c27a973c82
fix null negative_prompt on get requests
...
Small typo that causes a bug when returning negative prompts from the get request.
2022-11-22 14:02:59 +00:00
745f1e8f80
[CLIP interrogator] use local file, if available
2022-11-22 12:48:25 +00:00
210cb4c128
Use GPU for loading safetensors, disable export
2022-11-21 16:40:18 -05:00
162fef394f
Patch line ui endings
2022-11-21 10:50:57 -05:00
0efffbb407
Supporting `*.safetensors` format.
...
If a model file exists with extension `.safetensors` then we can load it
more safely than with PyTorch weights.
2022-11-21 14:04:25 +01:00
563ea3f6ff
Change .cuda() to .to(devices.device)
2022-11-21 02:56:00 -05:00
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)
2022-11-21 02:07:19 -05:00
9ae30b3450
remove cmd args requirement for deepdanbooru
2022-11-21 12:53:55 +09:00
5b57f61ba4
fix pin_memory with different latent sampling method
2022-11-21 10:15:46 +09:00
637815632f
Generalize SD torch load/save to implement safetensor merging compat
2022-11-20 13:36:05 -05:00
828438b4a1
Merge pull request #4120 from aliencaocao/enable-override-hypernet
...
Enable override_settings to take effect for hypernetworks
2022-11-20 16:49:06 +03:00
c81d440d87
moved deepdanbooru to pure pytorch implementation
2022-11-20 16:39:20 +03:00
AUTOMATIC1111