lambert/style-aligned
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sdxl demo

Browse Source
This commit is contained in:
amirhertz
2023-11-28 15:52:03 +02:00
commit e9cc56a475
4 changed files with 604 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
LICENSE
+202
View File
@@ -0,0 +1,202 @@
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 [yyyy] [name of copyright owner]
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.
contributing.md
+28
View File
@@ -0,0 +1,28 @@
# How to Contribute
We'd love to accept your patches and contributions to this project. There are
just a few small guidelines you need to follow.
## Contributor License Agreement
Contributions to this project must be accompanied by a Contributor License
Agreement. You (or your employer) retain the copyright to your contribution;
this simply gives us permission to use and redistribute your contributions as
part of the project. Head over to <https://cla.developers.google.com/> to see
your current agreements on file or to sign a new one.
You generally only need to submit a CLA once, so if you've already submitted one
(even if it was for a different project), you probably don't need to do it
again.
## Code Reviews
All submissions, including submissions by project members, require review. We
use GitHub pull requests for this purpose. Consult
[GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
information on using pull requests.
## Community Guidelines
This project follows [Google's Open Source Community
Guidelines](https://opensource.google/conduct/).
sa_handler.py
+269
View File
@@ -0,0 +1,269 @@
# Copyright 2023 Google LLC
#
# 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.
from __future__ import annotations
from dataclasses import dataclass
from diffusers import StableDiffusionXLPipeline
import torch
import torch.nn as nn
from torch.nn import functional as nnf
from diffusers.models import attention_processor
import einops
T = torch.Tensor
@dataclass(frozen=True)
class StyleAlignedArgs:
share_group_norm: bool = True
share_layer_norm: bool = True,
share_attention: bool = True
adain_queries: bool = True
adain_keys: bool = True
adain_values: bool = False
full_attention_share: bool = False
keys_scale: float = 1.
only_self_level: float = 0.
def expand_first(feat: T, scale=1., ) -> T:
b = feat.shape[0]
feat_style = torch.stack((feat[0], feat[b // 2])).unsqueeze(1)
if scale == 1:
feat_style = feat_style.expand(2, b // 2, *feat.shape[1:])
else:
feat_style = feat_style.repeat(1, b // 2, 1, 1, 1)
feat_style = torch.cat([feat_style[:, :1], scale * feat_style[:, 1:]], dim=1)
return feat_style.reshape(*feat.shape)
def concat_first(feat: T, dim=2, scale=1.) -> T:
feat_style = expand_first(feat, scale=scale)
return torch.cat((feat, feat_style), dim=dim)
def calc_mean_std(feat, eps: float = 1e-5) -> tuple[T, T]:
feat_std = (feat.var(dim=-2, keepdims=True) + eps).sqrt()
feat_mean = feat.mean(dim=-2, keepdims=True)
return feat_mean, feat_std
def adain(feat: T) -> T:
feat_mean, feat_std = calc_mean_std(feat)
feat_style_mean = expand_first(feat_mean)
feat_style_std = expand_first(feat_std)
feat = (feat - feat_mean) / feat_std
feat = feat * feat_style_std + feat_style_mean
return feat
class DefaultAttentionProcessor(nn.Module):
def __init__(self):
super().__init__()
self.processor = attention_processor.AttnProcessor2_0()
def __call__(self, attn: attention_processor.Attention, hidden_states, encoder_hidden_states=None,
attention_mask=None, **kwargs):
return self.processor(attn, hidden_states, encoder_hidden_states, attention_mask)
class SharedAttentionProcessor(DefaultAttentionProcessor):
def shared_call(
self,
attn: attention_processor.Attention,
hidden_states,
encoder_hidden_states=None,
attention_mask=None,
**kwargs
):
residual = hidden_states
input_ndim = hidden_states.ndim
if input_ndim == 4:
batch_size, channel, height, width = hidden_states.shape
hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
batch_size, sequence_length, _ = (
hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
)
if attention_mask is not None:
attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
# scaled_dot_product_attention expects attention_mask shape to be
# (batch, heads, source_length, target_length)
attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
query = attn.to_q(hidden_states)
key = attn.to_k(hidden_states)
value = attn.to_v(hidden_states)
inner_dim = key.shape[-1]
head_dim = inner_dim // attn.heads
query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
# if self.step >= self.start_inject:
if self.adain_queries:
query = adain(query)
if self.adain_keys:
key = adain(key)
if self.adain_values:
value = adain(value)
if self.share_attention:
key = concat_first(key, -2, scale=self.keys_scale)
value = concat_first(value, -2)
hidden_states = nnf.scaled_dot_product_attention(
query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
)
else:
hidden_states = nnf.scaled_dot_product_attention(
query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
)
# hidden_states = adain(hidden_states)
hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
hidden_states = hidden_states.to(query.dtype)
# linear proj
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
if input_ndim == 4:
hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
if attn.residual_connection:
hidden_states = hidden_states + residual
hidden_states = hidden_states / attn.rescale_output_factor
return hidden_states
def __call__(self, attn: attention_processor.Attention, hidden_states, encoder_hidden_states=None,
attention_mask=None, **kwargs):
if self.full_attention_share:
b, n, d = hidden_states.shape
hidden_states = einops.rearrange(hidden_states, '(k b) n d -> k (b n) d', k=2)
hidden_states = super().__call__(attn, hidden_states, encoder_hidden_states=encoder_hidden_states,
attention_mask=attention_mask, **kwargs)
hidden_states = einops.rearrange(hidden_states, 'k (b n) d -> (k b) n d', n=n)
else:
hidden_states = self.shared_call(attn, hidden_states, hidden_states, attention_mask, **kwargs)
return hidden_states
def __init__(self, style_aligned_args: StyleAlignedArgs):
super().__init__()
self.share_attention = style_aligned_args.share_attention
self.adain_queries = style_aligned_args.adain_queries
self.adain_keys = style_aligned_args.adain_keys
self.adain_values = style_aligned_args.adain_values
self.full_attention_share = style_aligned_args.full_attention_share
self.keys_scale = style_aligned_args.keys_scale
def _get_switch_vec(total_num_layers, level):
if level == 0:
return torch.zeros(total_num_layers, dtype=torch.bool)
if level == 1:
return torch.ones(total_num_layers, dtype=torch.bool)
to_flip = level > .5
if to_flip:
level = 1 - level
num_switch = int(level * total_num_layers)
vec = torch.arange(total_num_layers)
vec = vec % (total_num_layers // num_switch)
vec = vec == 0
if to_flip:
vec = ~vec
return vec
def init_attention_processors(pipeline: StableDiffusionXLPipeline, style_aligned_args: StyleAlignedArgs | None = None):
attn_procs = {}
unet = pipeline.unet
number_of_self, number_of_cross = 0, 0
num_self_layers = len([name for name in unet.attn_processors.keys() if 'attn1' in name])
if style_aligned_args is None:
only_self_vec = _get_switch_vec(num_self_layers, 1)
else:
only_self_vec = _get_switch_vec(num_self_layers, style_aligned_args.only_self_level)
for i, name in enumerate(unet.attn_processors.keys()):
is_self_attention = 'attn1' in name
if is_self_attention:
number_of_self += 1
if style_aligned_args is None or only_self_vec[i // 2]:
attn_procs[name] = DefaultAttentionProcessor()
else:
attn_procs[name] = SharedAttentionProcessor(style_aligned_args)
else:
number_of_cross += 1
attn_procs[name] = DefaultAttentionProcessor()
unet.set_attn_processor(attn_procs)
def register_shared_norm(pipeline: StableDiffusionXLPipeline,
share_group_norm: bool = True,
share_layer_norm: bool = True, ):
def register_norm_forward(norm_layer: nn.GroupNorm | nn.LayerNorm) -> nn.GroupNorm | nn.LayerNorm:
if not hasattr(norm_layer, 'orig_forward'):
setattr(norm_layer, 'orig_forward', norm_layer.forward)
orig_forward = norm_layer.orig_forward
def forward_(hidden_states: T) -> T:
n = hidden_states.shape[-2]
hidden_states = concat_first(hidden_states, dim=-2)
hidden_states = orig_forward(hidden_states)
return hidden_states[..., :n, :]
norm_layer.forward = forward_
return norm_layer
def get_norm_layers(pipeline_, norm_layers_: dict[str, list[nn.GroupNorm | nn.LayerNorm]]):
if isinstance(pipeline_, nn.LayerNorm) and share_layer_norm:
norm_layers_['layer'].append(pipeline_)
if isinstance(pipeline_, nn.GroupNorm) and share_group_norm:
norm_layers_['group'].append(pipeline_)
else:
for layer in pipeline_.children():
get_norm_layers(layer, norm_layers_)
norm_layers = {'group': [], 'layer': []}
get_norm_layers(pipeline.unet, norm_layers)
return [register_norm_forward(layer) for layer in norm_layers['group']] + [register_norm_forward(layer) for layer in
norm_layers['layer']]
class Handler:
def register(self, style_aligned_args: StyleAlignedArgs, ):
self.norm_layers = register_shared_norm(self.pipeline, style_aligned_args.share_group_norm,
style_aligned_args.share_layer_norm)
init_attention_processors(self.pipeline, style_aligned_args)
def remove(self):
for layer in self.norm_layers:
layer.forward = layer.orig_forward
self.norm_layers = []
init_attention_processors(self.pipeline, None)
def __init__(self, pipeline: StableDiffusionXLPipeline):
self.pipeline = pipeline
self.norm_layers = []
style_aligned_sdxl.ipynb
+105
View File
File diff suppressed because one or more lines are too long