0cc5f380d5
even more clarifications(?)
...
i have no idea what commit message should be
3 years ago
2de99d62dd
some clarification
3 years ago
dc0f05c57c
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
57096823fa
Remove a stacktrace from an assertion to not scare people
3 years ago
15e89ef0f6
fix for unet hijack breaking the train tab
3 years ago
2d92d05ca2
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
e425b9812b
Added Python version check
3 years ago
789d47f832
make clicking extra networks button one more time close the extra networks UI
3 years ago
e179b6098a
allow symlinks in the textual inversion embeddings folder
3 years ago
635499e832
add pix2pix credits
3 years ago
1574e96729
Merge pull request #6510 from brkirch/unet16-upcast-precision
...
Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half
3 years ago
1982ef6890
Merge pull request #7138 from mykeehu/patch-4
...
Fix extra network thumbs label color
3 years ago
57c1baa774
change to code for live preview fix on OSX to be bit more obvious
3 years ago
23dafe6d86
Merge pull request #7151 from brkirch/fix-approx-nn
...
Fix Approx NN previews changing first generation result
3 years ago
11485659dc
Merge pull request #7195 from Klace/instruct-pix2pix_model_load
...
Add instruct-pix2pix hijack
3 years ago
bd9b55ee90
Update requirements transformers==4.25.1
...
Update requirement for transformers to version 4.25.1 to allow instruct-pix2pix demo code to work
3 years ago
ee0a0da324
Add instruct-pix2pix hijack
...
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
3 years ago
d5ce044bcd
Merge pull request #7146 from EllangoK/master
...
Adds X/Y/Z Grid Script
3 years ago
1bfec873fa
add an experimental option to apply loras to outputs rather than inputs
3 years ago
e3b53fd295
Add UI setting for upcasting attention to float32
...
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.
3 years ago
84d9ce30cb
Add option for float32 sampling with float16 UNet
...
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().
3 years ago
48a15821de
remove the pip install stuff because it does not work as i hoped it would
3 years ago
bef1931895
add fastapi to requirements
3 years ago
93fad28a97
print progress when installing torch
...
add PIP_INSTALLER_LOCATION env var to install pip if it's not installed
remove accidental call to accelerate when venv is disabled
add another env var to skip venv - SKIP_VENV
3 years ago
5228ec8bda
remove fairscale requirement, add fake fairscale to make BLIP not complain about it mk2
3 years ago
28189985e6
remove fairscale requirement, add fake fairscale to make BLIP not complain about it
3 years ago
dac45299dd
make git commands not fail for extensions when you have spaces in webui directory
3 years ago
ec8774729e
swaps xyz axes internally if one costs more
3 years ago
e46bfa5a9e
handling sub grids and merging into one
3 years ago
9fc354e130
implements most of xyz grid script
3 years ago
d30ac02f28
renamed xy to xyz grid
...
this is mostly just so git can detect it properly
3 years ago
602a1864b0
also return the removed field to sdapi/v1/upscalers because someone might have relied on it existing
3 years ago
42a70d7477
repair sdapi/v1/upscalers returning bogus results
3 years ago
8b903322e6
Merge pull request #7140 from vladmandic/api-decode-image
...
Add exception handling to API image decode
3 years ago
848ef919b3
Merge pull request #7144 from catboxanon/swinir-interrupt
...
Make SwinIR upscaler interruptible and skippable
3 years ago
393e09c1c3
Merge pull request #7148 from acncagua/improvement_launch.py
...
Set Linux xformers 0.0.16RC425
3 years ago
f64af77adc
Fix different first gen with Approx NN previews
...
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.
3 years ago
078e16e4d3
Set Linux xformers 0.0.16RC425
3 years ago
3c47b05036
Also make SwinIR skippable
3 years ago
f993525820
Make SwinIR interruptible
3 years ago
45e270dfc8
add image decod exception handling
3 years ago
82a28bfe35
Fix extra network thumbs label color
...
Added white color for labels.
3 years ago
5c1cb9263f
fix BLIP failing to import depending on configuration
3 years ago
7ba7f4ed6e
Merge pull request #7113 from vladmandic/interrogate
...
Add selector to interrogate categories
3 years ago
7b1c7ba87b
add support for apostrophe in extra network names
3 years ago
865af20d8a
suppress A matching Triton is not available message
...
you can all now stop worrying about it
3 years ago
04a561c11c
add option to skip interrogate categories
3 years ago
efa7287be0
Merge branch 'AUTOMATIC1111:master' into interrogate
3 years ago
c6f20f7262
make loras before 0.4.0 ALSO work
3 years ago
171a5b3bb9
Merge pull request #7032 from gmq/extra-network-styles
...
Extra network view style
3 years ago
Spaceginner
AUTOMATIC
Alex "mcmonkey" Goodwin
Kyle
brkirch
EllangoK
acncagua
catboxanon
Vladimir Mandic
Mykeehu