mrq/stable-diffusion-webui
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added licenses screen to settings

Browse Source 
added footer
removed unused inpainting code
This commit is contained in:
AUTOMATIC 2023-01-03 20:23:17 +03:00
parent 8f96f92899
commit 82cfc227d7
6 changed files with 427 additions and 234 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -127,6 +127,8 @@ Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki). The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
## Credits ## Credits
Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers - Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git - k-diffusion - https://github.com/crowsonkb/k-diffusion.git
- GFPGAN - https://github.com/TencentARC/GFPGAN.git - GFPGAN - https://github.com/TencentARC/GFPGAN.git

9
html/footer.html Normal file
View File

@ -0,0 +1,9 @@
<div>
<a href="/docs">API</a>
 • 
<a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">Github</a>
 • 
<a href="https://gradio.app">Gradio</a>
 • 
<a href="/" onclick="javascript:gradioApp().getElementById('settings_restart_gradio').click(); return false">Reload UI</a>
</div>

392
html/licenses.html Normal file
View File

@ -0,0 +1,392 @@
<style>
#licenses h2 {font-size: 1.2em; font-weight: bold; margin-bottom: 0.2em;}
#licenses small {font-size: 0.95em; opacity: 0.85;}
#licenses pre { margin: 1em 0 2em 0;}
</style>
<h2><a href="https://github.com/sczhou/CodeFormer/blob/master/LICENSE">CodeFormer</a></h2>
<small>Parts of CodeFormer code had to be copied to be compatible with GFPGAN.</small>
<pre>
S-Lab License 1.0
Copyright 2022 S-Lab
Redistribution and use for non-commercial purpose in source and
binary forms, with or without modification, are permitted provided
that the following conditions are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in
the documentation and/or other materials provided with the
distribution.
3. Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
In the event that redistribution and/or use for commercial purpose in
source or binary forms, with or without modification is required,
please contact the contributor(s) of the work.
</pre>
<h2><a href="https://github.com/victorca25/iNNfer/blob/main/LICENSE">ESRGAN</a></h2>
<small>Code for architecture and reading models copied.</small>
<pre>
MIT License
Copyright (c) 2021 victorca25
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE">Real-ESRGAN</a></h2>
<small>Some code is copied to support ESRGAN models.</small>
<pre>
BSD 3-Clause License
Copyright (c) 2021, Xintao Wang
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
</pre>
<h2><a href="https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE">InvokeAI</a></h2>
<small>Some code for compatibility with OSX is taken from lstein's repository.</small>
<pre>
MIT License
Copyright (c) 2022 InvokeAI Team
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/Hafiidz/latent-diffusion/blob/main/LICENSE">LDSR</a></h2>
<small>Code added by contirubtors, most likely copied from this repository.</small>
<pre>
MIT License
Copyright (c) 2022 Machine Vision and Learning Group, LMU Munich
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/pharmapsychotic/clip-interrogator/blob/main/LICENSE">CLIP Interrogator</a></h2>
<small>Some small amounts of code borrowed and reworked.</small>
<pre>
MIT License
Copyright (c) 2022 pharmapsychotic
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
</pre>
<h2><a href="https://github.com/JingyunLiang/SwinIR/blob/main/LICENSE">SwinIR</a></h2>
<small>Code added by contirubtors, most likely copied from this repository.</small>
<pre>
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [2021] [SwinIR Authors]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
</pre>

232
modules/sd_hijack_inpainting.py
View File

@ -12,191 +12,6 @@ from ldm.models.diffusion.ddpm import LatentDiffusion
from ldm.models.diffusion.plms import PLMSSampler from ldm.models.diffusion.plms import PLMSSampler
from ldm.models.diffusion.ddim import DDIMSampler, noise_like from ldm.models.diffusion.ddim import DDIMSampler, noise_like
# =================================================================================================
# Monkey patch DDIMSampler methods from RunwayML repo directly.
# Adapted from:
# https://github.com/runwayml/stable-diffusion/blob/main/ldm/models/diffusion/ddim.py
# =================================================================================================
@torch.no_grad()
def sample_ddim(self,
S,
batch_size,
shape,
conditioning=None,
callback=None,
normals_sequence=None,
img_callback=None,
quantize_x0=False,
eta=0.,
mask=None,
x0=None,
temperature=1.,
noise_dropout=0.,
score_corrector=None,
corrector_kwargs=None,
verbose=True,
x_T=None,
log_every_t=100,
unconditional_guidance_scale=1.,
unconditional_conditioning=None,
# this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
**kwargs
):
if conditioning is not None:
if isinstance(conditioning, dict):
ctmp = conditioning[list(conditioning.keys())[0]]
while isinstance(ctmp, list):
ctmp = ctmp[0]
cbs = ctmp.shape[0]
if cbs != batch_size:
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
else:
if conditioning.shape[0] != batch_size:
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
# sampling
C, H, W = shape
size = (batch_size, C, H, W)
print(f'Data shape for DDIM sampling is {size}, eta {eta}')
samples, intermediates = self.ddim_sampling(conditioning, size,
callback=callback,
img_callback=img_callback,
quantize_denoised=quantize_x0,
mask=mask, x0=x0,
ddim_use_original_steps=False,
noise_dropout=noise_dropout,
temperature=temperature,
score_corrector=score_corrector,
corrector_kwargs=corrector_kwargs,
x_T=x_T,
log_every_t=log_every_t,
unconditional_guidance_scale=unconditional_guidance_scale,
unconditional_conditioning=unconditional_conditioning,
)
return samples, intermediates
@torch.no_grad()
def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
unconditional_guidance_scale=1., unconditional_conditioning=None):
b, *_, device = *x.shape, x.device
if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
e_t = self.model.apply_model(x, t, c)
else:
x_in = torch.cat([x] * 2)
t_in = torch.cat([t] * 2)
if isinstance(c, dict):
assert isinstance(unconditional_conditioning, dict)
c_in = dict()
for k in c:
if isinstance(c[k], list):
c_in[k] = [
torch.cat([unconditional_conditioning[k][i], c[k][i]])
for i in range(len(c[k]))
]
else:
c_in[k] = torch.cat([unconditional_conditioning[k], c[k]])
else:
c_in = torch.cat([unconditional_conditioning, c])
e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
if score_corrector is not None:
assert self.model.parameterization == "eps"
e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
# select parameters corresponding to the currently considered timestep
a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
# current prediction for x_0
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
if quantize_denoised:
pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
# direction pointing to x_t
dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
if noise_dropout > 0.:
noise = torch.nn.functional.dropout(noise, p=noise_dropout)
x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
return x_prev, pred_x0
# =================================================================================================
# Monkey patch PLMSSampler methods.
# This one was not actually patched correctly in the RunwayML repo, but we can replicate the changes.
# Adapted from:
# https://github.com/CompVis/stable-diffusion/blob/main/ldm/models/diffusion/plms.py
# =================================================================================================
@torch.no_grad()
def sample_plms(self,
S,
batch_size,
shape,
conditioning=None,
callback=None,
normals_sequence=None,
img_callback=None,
quantize_x0=False,
eta=0.,
mask=None,
x0=None,
temperature=1.,
noise_dropout=0.,
score_corrector=None,
corrector_kwargs=None,
verbose=True,
x_T=None,
log_every_t=100,
unconditional_guidance_scale=1.,
unconditional_conditioning=None,
# this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
**kwargs
):
if conditioning is not None:
if isinstance(conditioning, dict):
ctmp = conditioning[list(conditioning.keys())[0]]
while isinstance(ctmp, list):
ctmp = ctmp[0]
cbs = ctmp.shape[0]
if cbs != batch_size:
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
else:
if conditioning.shape[0] != batch_size:
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
# sampling
C, H, W = shape
size = (batch_size, C, H, W)
# print(f'Data shape for PLMS sampling is {size}') # remove unnecessary message
samples, intermediates = self.plms_sampling(conditioning, size,
callback=callback,
img_callback=img_callback,
quantize_denoised=quantize_x0,
mask=mask, x0=x0,
ddim_use_original_steps=False,
noise_dropout=noise_dropout,
temperature=temperature,
score_corrector=score_corrector,
corrector_kwargs=corrector_kwargs,
x_T=x_T,
log_every_t=log_every_t,
unconditional_guidance_scale=unconditional_guidance_scale,
unconditional_conditioning=unconditional_conditioning,
)
return samples, intermediates
@torch.no_grad() @torch.no_grad()
def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False, def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
@ -280,44 +95,6 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F
return x_prev, pred_x0, e_t return x_prev, pred_x0, e_t
# =================================================================================================
# Monkey patch LatentInpaintDiffusion to load the checkpoint with a proper config.
# Adapted from:
# https://github.com/runwayml/stable-diffusion/blob/main/ldm/models/diffusion/ddpm.py
# =================================================================================================
@torch.no_grad()
def get_unconditional_conditioning(self, batch_size, null_label=None):
if null_label is not None:
xc = null_label
if isinstance(xc, ListConfig):
xc = list(xc)
if isinstance(xc, dict) or isinstance(xc, list):
c = self.get_learned_conditioning(xc)
else:
if hasattr(xc, "to"):
xc = xc.to(self.device)
c = self.get_learned_conditioning(xc)
else:
# todo: get null label from cond_stage_model
raise NotImplementedError()
c = repeat(c, "1 ... -> b ...", b=batch_size).to(self.device)
return c
class LatentInpaintDiffusion(LatentDiffusion):
def __init__(
self,
concat_keys=("mask", "masked_image"),
masked_image_key="masked_image",
*args,
**kwargs,
):
super().__init__(*args, **kwargs)
self.masked_image_key = masked_image_key
assert self.masked_image_key in concat_keys
self.concat_keys = concat_keys
def should_hijack_inpainting(checkpoint_info): def should_hijack_inpainting(checkpoint_info):
ckpt_basename = os.path.basename(checkpoint_info.filename).lower() ckpt_basename = os.path.basename(checkpoint_info.filename).lower()
@ -326,15 +103,6 @@ def should_hijack_inpainting(checkpoint_info):
def do_inpainting_hijack(): def do_inpainting_hijack():
# most of this stuff seems to no longer be needed because it is already included into SD2.0
# p_sample_plms is needed because PLMS can't work with dicts as conditionings # p_sample_plms is needed because PLMS can't work with dicts as conditionings
# this file should be cleaned up later if everything turns out to work fine
# ldm.models.diffusion.ddpm.get_unconditional_conditioning = get_unconditional_conditioning
# ldm.models.diffusion.ddpm.LatentInpaintDiffusion = LatentInpaintDiffusion
# ldm.models.diffusion.ddim.DDIMSampler.p_sample_ddim = p_sample_ddim
# ldm.models.diffusion.ddim.DDIMSampler.sample = sample_ddim
ldm.models.diffusion.plms.PLMSSampler.p_sample_plms = p_sample_plms ldm.models.diffusion.plms.PLMSSampler.p_sample_plms = p_sample_plms
# ldm.models.diffusion.plms.PLMSSampler.sample = sample_plms

15
modules/ui.py
View File

@ -1529,8 +1529,10 @@ def create_ui():
with gr.Blocks(analytics_enabled=False) as settings_interface: with gr.Blocks(analytics_enabled=False) as settings_interface:
with gr.Row(): with gr.Row():
settings_submit = gr.Button(value="Apply settings", variant='primary', elem_id="settings_submit") with gr.Column(scale=6):
restart_gradio = gr.Button(value='Restart UI', variant='primary', elem_id="settings_restart_gradio") settings_submit = gr.Button(value="Apply settings", variant='primary', elem_id="settings_submit")
with gr.Column():
restart_gradio = gr.Button(value='Reload UI', variant='primary', elem_id="settings_restart_gradio")
result = gr.HTML(elem_id="settings_result") result = gr.HTML(elem_id="settings_result")
@ -1574,6 +1576,11 @@ def create_ui():
download_localization = gr.Button(value='Download localization template', elem_id="download_localization") download_localization = gr.Button(value='Download localization template', elem_id="download_localization")
reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary', elem_id="settings_reload_script_bodies") reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary', elem_id="settings_reload_script_bodies")
if os.path.exists("html/licenses.html"):
with open("html/licenses.html", encoding="utf8") as file:
with gr.TabItem("Licenses"):
gr.HTML(file.read(), elem_id="licenses")
gr.Button(value="Show all pages", elem_id="settings_show_all_pages") gr.Button(value="Show all pages", elem_id="settings_show_all_pages")
request_notifications.click( request_notifications.click(
@ -1659,6 +1666,10 @@ def create_ui():
if os.path.exists(os.path.join(script_path, "notification.mp3")): if os.path.exists(os.path.join(script_path, "notification.mp3")):
audio_notification = gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False) audio_notification = gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False)
if os.path.exists("html/footer.html"):
with open("html/footer.html", encoding="utf8") as file:
gr.HTML(file.read(), elem_id="footer")
text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False) text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False)
settings_submit.click( settings_submit.click(
fn=wrap_gradio_call(run_settings, extra_outputs=[gr.update()]), fn=wrap_gradio_call(run_settings, extra_outputs=[gr.update()]),

11
style.css
View File

@ -616,6 +616,17 @@ img2maskimg, #img2maskimg > .h-60, #img2maskimg > .h-60 > div, #img2maskimg > .h
padding-bottom: 0.5em; padding-bottom: 0.5em;
} }
footer {
display: none !important;
}
#footer{
text-align: center;
}
#footer div{
display: inline-block;
}
/* The following handles localization for right-to-left (RTL) languages like Arabic. /* The following handles localization for right-to-left (RTL) languages like Arabic.
The rtl media type will only be activated by the logic in javascript/localization.js. The rtl media type will only be activated by the logic in javascript/localization.js.