Merge branch 'AUTOMATIC1111:master' into fix-sd-arch-switch-in-override-settings
Philpax
3 years ago
committed by
GitHub
commit
83ca8dd0c9
@ -0,0 +1,72 @@
|
||||
model:
|
||||
base_learning_rate: 1.0e-04
|
||||
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
||||
params:
|
||||
linear_start: 0.00085
|
||||
linear_end: 0.0120
|
||||
num_timesteps_cond: 1
|
||||
log_every_t: 200
|
||||
timesteps: 1000
|
||||
first_stage_key: "jpg"
|
||||
cond_stage_key: "txt"
|
||||
image_size: 64
|
||||
channels: 4
|
||||
cond_stage_trainable: false # Note: different from the one we trained before
|
||||
conditioning_key: crossattn
|
||||
monitor: val/loss_simple_ema
|
||||
scale_factor: 0.18215
|
||||
use_ema: False
|
||||
|
||||
scheduler_config: # 10000 warmup steps
|
||||
target: ldm.lr_scheduler.LambdaLinearScheduler
|
||||
params:
|
||||
warm_up_steps: [ 10000 ]
|
||||
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
||||
f_start: [ 1.e-6 ]
|
||||
f_max: [ 1. ]
|
||||
f_min: [ 1. ]
|
||||
|
||||
unet_config:
|
||||
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||||
params:
|
||||
image_size: 32 # unused
|
||||
in_channels: 4
|
||||
out_channels: 4
|
||||
model_channels: 320
|
||||
attention_resolutions: [ 4, 2, 1 ]
|
||||
num_res_blocks: 2
|
||||
channel_mult: [ 1, 2, 4, 4 ]
|
||||
num_heads: 8
|
||||
use_spatial_transformer: True
|
||||
transformer_depth: 1
|
||||
context_dim: 768
|
||||
use_checkpoint: True
|
||||
legacy: False
|
||||
|
||||
first_stage_config:
|
||||
target: ldm.models.autoencoder.AutoencoderKL
|
||||
params:
|
||||
embed_dim: 4
|
||||
monitor: val/rec_loss
|
||||
ddconfig:
|
||||
double_z: true
|
||||
z_channels: 4
|
||||
resolution: 256
|
||||
in_channels: 3
|
||||
out_ch: 3
|
||||
ch: 128
|
||||
ch_mult:
|
||||
- 1
|
||||
- 2
|
||||
- 4
|
||||
- 4
|
||||
num_res_blocks: 2
|
||||
attn_resolutions: []
|
||||
dropout: 0.0
|
||||
lossconfig:
|
||||
target: torch.nn.Identity
|
||||
|
||||
cond_stage_config:
|
||||
target: modules.xlmr.BertSeriesModelWithTransformation
|
||||
params:
|
||||
name: "XLMR-Large"
|
||||
@ -0,0 +1,50 @@
|
||||
import random
|
||||
|
||||
from modules import script_callbacks, shared
|
||||
import gradio as gr
|
||||
|
||||
art_symbol = '\U0001f3a8' # 🎨
|
||||
global_prompt = None
|
||||
related_ids = {"txt2img_prompt", "txt2img_clear_prompt", "img2img_prompt", "img2img_clear_prompt" }
|
||||
|
||||
|
||||
def roll_artist(prompt):
|
||||
allowed_cats = set([x for x in shared.artist_db.categories() if len(shared.opts.random_artist_categories)==0 or x in shared.opts.random_artist_categories])
|
||||
artist = random.choice([x for x in shared.artist_db.artists if x.category in allowed_cats])
|
||||
|
||||
return prompt + ", " + artist.name if prompt != '' else artist.name
|
||||
|
||||
|
||||
def add_roll_button(prompt):
|
||||
roll = gr.Button(value=art_symbol, elem_id="roll", visible=len(shared.artist_db.artists) > 0)
|
||||
|
||||
roll.click(
|
||||
fn=roll_artist,
|
||||
_js="update_txt2img_tokens",
|
||||
inputs=[
|
||||
prompt,
|
||||
],
|
||||
outputs=[
|
||||
prompt,
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
def after_component(component, **kwargs):
|
||||
global global_prompt
|
||||
|
||||
elem_id = kwargs.get('elem_id', None)
|
||||
if elem_id not in related_ids:
|
||||
return
|
||||
|
||||
if elem_id == "txt2img_prompt":
|
||||
global_prompt = component
|
||||
elif elem_id == "txt2img_clear_prompt":
|
||||
add_roll_button(global_prompt)
|
||||
elif elem_id == "img2img_prompt":
|
||||
global_prompt = component
|
||||
elif elem_id == "img2img_clear_prompt":
|
||||
add_roll_button(global_prompt)
|
||||
|
||||
|
||||
script_callbacks.on_after_component(after_component)
|
||||
@ -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>
|
||||
@ -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>
|
||||
|
||||
@ -0,0 +1,34 @@
|
||||
import open_clip.tokenizer
|
||||
import torch
|
||||
|
||||
from modules import sd_hijack_clip, devices
|
||||
from modules.shared import opts
|
||||
|
||||
|
||||
class FrozenXLMREmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords):
|
||||
def __init__(self, wrapped, hijack):
|
||||
super().__init__(wrapped, hijack)
|
||||
|
||||
self.id_start = wrapped.config.bos_token_id
|
||||
self.id_end = wrapped.config.eos_token_id
|
||||
self.id_pad = wrapped.config.pad_token_id
|
||||
|
||||
self.comma_token = self.tokenizer.get_vocab().get(',', None) # alt diffusion doesn't have </w> bits for comma
|
||||
|
||||
def encode_with_transformers(self, tokens):
|
||||
# there's no CLIP Skip here because all hidden layers have size of 1024 and the last one uses a
|
||||
# trained layer to transform those 1024 into 768 for unet; so you can't choose which transformer
|
||||
# layer to work with - you have to use the last
|
||||
|
||||
attention_mask = (tokens != self.id_pad).to(device=tokens.device, dtype=torch.int64)
|
||||
features = self.wrapped(input_ids=tokens, attention_mask=attention_mask)
|
||||
z = features['projection_state']
|
||||
|
||||
return z
|
||||
|
||||
def encode_embedding_init_text(self, init_text, nvpt):
|
||||
embedding_layer = self.wrapped.roberta.embeddings
|
||||
ids = self.wrapped.tokenizer(init_text, max_length=nvpt, return_tensors="pt", add_special_tokens=False)["input_ids"]
|
||||
embedded = embedding_layer.token_embedding.wrapped(ids.to(devices.device)).squeeze(0)
|
||||
|
||||
return embedded
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,25 @@
|
||||
import gradio as gr
|
||||
|
||||
|
||||
class ToolButton(gr.Button, gr.components.FormComponent):
|
||||
"""Small button with single emoji as text, fits inside gradio forms"""
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(variant="tool", **kwargs)
|
||||
|
||||
def get_block_name(self):
|
||||
return "button"
|
||||
|
||||
|
||||
class FormRow(gr.Row, gr.components.FormComponent):
|
||||
"""Same as gr.Row but fits inside gradio forms"""
|
||||
|
||||
def get_block_name(self):
|
||||
return "row"
|
||||
|
||||
|
||||
class FormGroup(gr.Group, gr.components.FormComponent):
|
||||
"""Same as gr.Row but fits inside gradio forms"""
|
||||
|
||||
def get_block_name(self):
|
||||
return "group"
|
||||
@ -0,0 +1,137 @@
|
||||
from transformers import BertPreTrainedModel,BertModel,BertConfig
|
||||
import torch.nn as nn
|
||||
import torch
|
||||
from transformers.models.xlm_roberta.configuration_xlm_roberta import XLMRobertaConfig
|
||||
from transformers import XLMRobertaModel,XLMRobertaTokenizer
|
||||
from typing import Optional
|
||||
|
||||
class BertSeriesConfig(BertConfig):
|
||||
def __init__(self, vocab_size=30522, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act="gelu", hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, pad_token_id=0, position_embedding_type="absolute", use_cache=True, classifier_dropout=None,project_dim=512, pooler_fn="average",learn_encoder=False,model_type='bert',**kwargs):
|
||||
|
||||
super().__init__(vocab_size, hidden_size, num_hidden_layers, num_attention_heads, intermediate_size, hidden_act, hidden_dropout_prob, attention_probs_dropout_prob, max_position_embeddings, type_vocab_size, initializer_range, layer_norm_eps, pad_token_id, position_embedding_type, use_cache, classifier_dropout, **kwargs)
|
||||
self.project_dim = project_dim
|
||||
self.pooler_fn = pooler_fn
|
||||
self.learn_encoder = learn_encoder
|
||||
|
||||
class RobertaSeriesConfig(XLMRobertaConfig):
|
||||
def __init__(self, pad_token_id=1, bos_token_id=0, eos_token_id=2,project_dim=512,pooler_fn='cls',learn_encoder=False, **kwargs):
|
||||
super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|
||||
self.project_dim = project_dim
|
||||
self.pooler_fn = pooler_fn
|
||||
self.learn_encoder = learn_encoder
|
||||
|
||||
|
||||
class BertSeriesModelWithTransformation(BertPreTrainedModel):
|
||||
|
||||
_keys_to_ignore_on_load_unexpected = [r"pooler"]
|
||||
_keys_to_ignore_on_load_missing = [r"position_ids", r"predictions.decoder.bias"]
|
||||
config_class = BertSeriesConfig
|
||||
|
||||
def __init__(self, config=None, **kargs):
|
||||
# modify initialization for autoloading
|
||||
if config is None:
|
||||
config = XLMRobertaConfig()
|
||||
config.attention_probs_dropout_prob= 0.1
|
||||
config.bos_token_id=0
|
||||
config.eos_token_id=2
|
||||
config.hidden_act='gelu'
|
||||
config.hidden_dropout_prob=0.1
|
||||
config.hidden_size=1024
|
||||
config.initializer_range=0.02
|
||||
config.intermediate_size=4096
|
||||
config.layer_norm_eps=1e-05
|
||||
config.max_position_embeddings=514
|
||||
|
||||
config.num_attention_heads=16
|
||||
config.num_hidden_layers=24
|
||||
config.output_past=True
|
||||
config.pad_token_id=1
|
||||
config.position_embedding_type= "absolute"
|
||||
|
||||
config.type_vocab_size= 1
|
||||
config.use_cache=True
|
||||
config.vocab_size= 250002
|
||||
config.project_dim = 768
|
||||
config.learn_encoder = False
|
||||
super().__init__(config)
|
||||
self.roberta = XLMRobertaModel(config)
|
||||
self.transformation = nn.Linear(config.hidden_size,config.project_dim)
|
||||
self.pre_LN=nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
|
||||
self.tokenizer = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large')
|
||||
self.pooler = lambda x: x[:,0]
|
||||
self.post_init()
|
||||
|
||||
def encode(self,c):
|
||||
device = next(self.parameters()).device
|
||||
text = self.tokenizer(c,
|
||||
truncation=True,
|
||||
max_length=77,
|
||||
return_length=False,
|
||||
return_overflowing_tokens=False,
|
||||
padding="max_length",
|
||||
return_tensors="pt")
|
||||
text["input_ids"] = torch.tensor(text["input_ids"]).to(device)
|
||||
text["attention_mask"] = torch.tensor(
|
||||
text['attention_mask']).to(device)
|
||||
features = self(**text)
|
||||
return features['projection_state']
|
||||
|
||||
def forward(
|
||||
self,
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
encoder_hidden_states: Optional[torch.Tensor] = None,
|
||||
encoder_attention_mask: Optional[torch.Tensor] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
) :
|
||||
r"""
|
||||
"""
|
||||
|
||||
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
||||
|
||||
|
||||
outputs = self.roberta(
|
||||
input_ids=input_ids,
|
||||
attention_mask=attention_mask,
|
||||
token_type_ids=token_type_ids,
|
||||
position_ids=position_ids,
|
||||
head_mask=head_mask,
|
||||
inputs_embeds=inputs_embeds,
|
||||
encoder_hidden_states=encoder_hidden_states,
|
||||
encoder_attention_mask=encoder_attention_mask,
|
||||
output_attentions=output_attentions,
|
||||
output_hidden_states=True,
|
||||
return_dict=return_dict,
|
||||
)
|
||||
|
||||
# last module outputs
|
||||
sequence_output = outputs[0]
|
||||
|
||||
|
||||
# project every module
|
||||
sequence_output_ln = self.pre_LN(sequence_output)
|
||||
|
||||
# pooler
|
||||
pooler_output = self.pooler(sequence_output_ln)
|
||||
pooler_output = self.transformation(pooler_output)
|
||||
projection_state = self.transformation(outputs.last_hidden_state)
|
||||
|
||||
return {
|
||||
'pooler_output':pooler_output,
|
||||
'last_hidden_state':outputs.last_hidden_state,
|
||||
'hidden_states':outputs.hidden_states,
|
||||
'attentions':outputs.attentions,
|
||||
'projection_state':projection_state,
|
||||
'sequence_out': sequence_output
|
||||
}
|
||||
|
||||
|
||||
class RobertaSeriesModelWithTransformation(BertSeriesModelWithTransformation):
|
||||
base_model_prefix = 'roberta'
|
||||
config_class= RobertaSeriesConfig
|
||||
@ -0,0 +1,68 @@
|
||||
model:
|
||||
base_learning_rate: 1.0e-4
|
||||
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
||||
params:
|
||||
parameterization: "v"
|
||||
linear_start: 0.00085
|
||||
linear_end: 0.0120
|
||||
num_timesteps_cond: 1
|
||||
log_every_t: 200
|
||||
timesteps: 1000
|
||||
first_stage_key: "jpg"
|
||||
cond_stage_key: "txt"
|
||||
image_size: 64
|
||||
channels: 4
|
||||
cond_stage_trainable: false
|
||||
conditioning_key: crossattn
|
||||
monitor: val/loss_simple_ema
|
||||
scale_factor: 0.18215
|
||||
use_ema: False # we set this to false because this is an inference only config
|
||||
|
||||
unet_config:
|
||||
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||||
params:
|
||||
use_checkpoint: True
|
||||
use_fp16: True
|
||||
image_size: 32 # unused
|
||||
in_channels: 4
|
||||
out_channels: 4
|
||||
model_channels: 320
|
||||
attention_resolutions: [ 4, 2, 1 ]
|
||||
num_res_blocks: 2
|
||||
channel_mult: [ 1, 2, 4, 4 ]
|
||||
num_head_channels: 64 # need to fix for flash-attn
|
||||
use_spatial_transformer: True
|
||||
use_linear_in_transformer: True
|
||||
transformer_depth: 1
|
||||
context_dim: 1024
|
||||
legacy: False
|
||||
|
||||
first_stage_config:
|
||||
target: ldm.models.autoencoder.AutoencoderKL
|
||||
params:
|
||||
embed_dim: 4
|
||||
monitor: val/rec_loss
|
||||
ddconfig:
|
||||
#attn_type: "vanilla-xformers"
|
||||
double_z: true
|
||||
z_channels: 4
|
||||
resolution: 256
|
||||
in_channels: 3
|
||||
out_ch: 3
|
||||
ch: 128
|
||||
ch_mult:
|
||||
- 1
|
||||
- 2
|
||||
- 4
|
||||
- 4
|
||||
num_res_blocks: 2
|
||||
attn_resolutions: []
|
||||
dropout: 0.0
|
||||
lossconfig:
|
||||
target: torch.nn.Identity
|
||||
|
||||
cond_stage_config:
|
||||
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
||||
params:
|
||||
freeze: True
|
||||
layer: "penultimate"
|
||||
Loading…
Reference in New Issue