Spaces:
Runtime error
Runtime error
Duplicate from hysts/ControlNet
Browse filesCo-authored-by: hysts <[email protected]>
- .gitattributes +34 -0
- .gitignore +162 -0
- .gitmodules +3 -0
- .pre-commit-config.yaml +37 -0
- .style.yapf +5 -0
- ControlNet +1 -0
- LICENSE.ControlNet +201 -0
- README.md +14 -0
- app.py +77 -0
- gradio_canny2image.py +74 -0
- gradio_depth2image.py +68 -0
- gradio_fake_scribble2image.py +68 -0
- gradio_hed2image.py +68 -0
- gradio_hough2image.py +81 -0
- gradio_normal2image.py +75 -0
- gradio_pose2image.py +68 -0
- gradio_scribble2image.py +63 -0
- gradio_scribble2image_interactive.py +88 -0
- gradio_seg2image.py +69 -0
- model.py +725 -0
- patch +115 -0
- requirements.txt +18 -0
- style.css +3 -0
.gitattributes
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models/
|
2 |
+
|
3 |
+
# Byte-compiled / optimized / DLL files
|
4 |
+
__pycache__/
|
5 |
+
*.py[cod]
|
6 |
+
*$py.class
|
7 |
+
|
8 |
+
# C extensions
|
9 |
+
*.so
|
10 |
+
|
11 |
+
# Distribution / packaging
|
12 |
+
.Python
|
13 |
+
build/
|
14 |
+
develop-eggs/
|
15 |
+
dist/
|
16 |
+
downloads/
|
17 |
+
eggs/
|
18 |
+
.eggs/
|
19 |
+
lib/
|
20 |
+
lib64/
|
21 |
+
parts/
|
22 |
+
sdist/
|
23 |
+
var/
|
24 |
+
wheels/
|
25 |
+
share/python-wheels/
|
26 |
+
*.egg-info/
|
27 |
+
.installed.cfg
|
28 |
+
*.egg
|
29 |
+
MANIFEST
|
30 |
+
|
31 |
+
# PyInstaller
|
32 |
+
# Usually these files are written by a python script from a template
|
33 |
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
34 |
+
*.manifest
|
35 |
+
*.spec
|
36 |
+
|
37 |
+
# Installer logs
|
38 |
+
pip-log.txt
|
39 |
+
pip-delete-this-directory.txt
|
40 |
+
|
41 |
+
# Unit test / coverage reports
|
42 |
+
htmlcov/
|
43 |
+
.tox/
|
44 |
+
.nox/
|
45 |
+
.coverage
|
46 |
+
.coverage.*
|
47 |
+
.cache
|
48 |
+
nosetests.xml
|
49 |
+
coverage.xml
|
50 |
+
*.cover
|
51 |
+
*.py,cover
|
52 |
+
.hypothesis/
|
53 |
+
.pytest_cache/
|
54 |
+
cover/
|
55 |
+
|
56 |
+
# Translations
|
57 |
+
*.mo
|
58 |
+
*.pot
|
59 |
+
|
60 |
+
# Django stuff:
|
61 |
+
*.log
|
62 |
+
local_settings.py
|
63 |
+
db.sqlite3
|
64 |
+
db.sqlite3-journal
|
65 |
+
|
66 |
+
# Flask stuff:
|
67 |
+
instance/
|
68 |
+
.webassets-cache
|
69 |
+
|
70 |
+
# Scrapy stuff:
|
71 |
+
.scrapy
|
72 |
+
|
73 |
+
# Sphinx documentation
|
74 |
+
docs/_build/
|
75 |
+
|
76 |
+
# PyBuilder
|
77 |
+
.pybuilder/
|
78 |
+
target/
|
79 |
+
|
80 |
+
# Jupyter Notebook
|
81 |
+
.ipynb_checkpoints
|
82 |
+
|
83 |
+
# IPython
|
84 |
+
profile_default/
|
85 |
+
ipython_config.py
|
86 |
+
|
87 |
+
# pyenv
|
88 |
+
# For a library or package, you might want to ignore these files since the code is
|
89 |
+
# intended to run in multiple environments; otherwise, check them in:
|
90 |
+
# .python-version
|
91 |
+
|
92 |
+
# pipenv
|
93 |
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
94 |
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
95 |
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
96 |
+
# install all needed dependencies.
|
97 |
+
#Pipfile.lock
|
98 |
+
|
99 |
+
# poetry
|
100 |
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
101 |
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
102 |
+
# commonly ignored for libraries.
|
103 |
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
104 |
+
#poetry.lock
|
105 |
+
|
106 |
+
# pdm
|
107 |
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
108 |
+
#pdm.lock
|
109 |
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
110 |
+
# in version control.
|
111 |
+
# https://pdm.fming.dev/#use-with-ide
|
112 |
+
.pdm.toml
|
113 |
+
|
114 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
115 |
+
__pypackages__/
|
116 |
+
|
117 |
+
# Celery stuff
|
118 |
+
celerybeat-schedule
|
119 |
+
celerybeat.pid
|
120 |
+
|
121 |
+
# SageMath parsed files
|
122 |
+
*.sage.py
|
123 |
+
|
124 |
+
# Environments
|
125 |
+
.env
|
126 |
+
.venv
|
127 |
+
env/
|
128 |
+
venv/
|
129 |
+
ENV/
|
130 |
+
env.bak/
|
131 |
+
venv.bak/
|
132 |
+
|
133 |
+
# Spyder project settings
|
134 |
+
.spyderproject
|
135 |
+
.spyproject
|
136 |
+
|
137 |
+
# Rope project settings
|
138 |
+
.ropeproject
|
139 |
+
|
140 |
+
# mkdocs documentation
|
141 |
+
/site
|
142 |
+
|
143 |
+
# mypy
|
144 |
+
.mypy_cache/
|
145 |
+
.dmypy.json
|
146 |
+
dmypy.json
|
147 |
+
|
148 |
+
# Pyre type checker
|
149 |
+
.pyre/
|
150 |
+
|
151 |
+
# pytype static type analyzer
|
152 |
+
.pytype/
|
153 |
+
|
154 |
+
# Cython debug symbols
|
155 |
+
cython_debug/
|
156 |
+
|
157 |
+
# PyCharm
|
158 |
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
159 |
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
160 |
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
161 |
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
162 |
+
#.idea/
|
.gitmodules
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
[submodule "ControlNet"]
|
2 |
+
path = ControlNet
|
3 |
+
url = https://github.com/lllyasviel/ControlNet
|
.pre-commit-config.yaml
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
exclude: patch
|
2 |
+
repos:
|
3 |
+
- repo: https://github.com/pre-commit/pre-commit-hooks
|
4 |
+
rev: v4.2.0
|
5 |
+
hooks:
|
6 |
+
- id: check-executables-have-shebangs
|
7 |
+
- id: check-json
|
8 |
+
- id: check-merge-conflict
|
9 |
+
- id: check-shebang-scripts-are-executable
|
10 |
+
- id: check-toml
|
11 |
+
- id: check-yaml
|
12 |
+
- id: double-quote-string-fixer
|
13 |
+
- id: end-of-file-fixer
|
14 |
+
- id: mixed-line-ending
|
15 |
+
args: ['--fix=lf']
|
16 |
+
- id: requirements-txt-fixer
|
17 |
+
- id: trailing-whitespace
|
18 |
+
- repo: https://github.com/myint/docformatter
|
19 |
+
rev: v1.4
|
20 |
+
hooks:
|
21 |
+
- id: docformatter
|
22 |
+
args: ['--in-place']
|
23 |
+
- repo: https://github.com/pycqa/isort
|
24 |
+
rev: 5.12.0
|
25 |
+
hooks:
|
26 |
+
- id: isort
|
27 |
+
- repo: https://github.com/pre-commit/mirrors-mypy
|
28 |
+
rev: v0.991
|
29 |
+
hooks:
|
30 |
+
- id: mypy
|
31 |
+
args: ['--ignore-missing-imports']
|
32 |
+
additional_dependencies: ['types-python-slugify']
|
33 |
+
- repo: https://github.com/google/yapf
|
34 |
+
rev: v0.32.0
|
35 |
+
hooks:
|
36 |
+
- id: yapf
|
37 |
+
args: ['--parallel', '--in-place']
|
.style.yapf
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[style]
|
2 |
+
based_on_style = pep8
|
3 |
+
blank_line_before_nested_class_or_def = false
|
4 |
+
spaces_before_comment = 2
|
5 |
+
split_before_logical_operator = true
|
ControlNet
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
Subproject commit f4748e3630d8141d7765e2bd9b1e348f47847707
|
LICENSE.ControlNet
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Apache License
|
2 |
+
Version 2.0, January 2004
|
3 |
+
http://www.apache.org/licenses/
|
4 |
+
|
5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6 |
+
|
7 |
+
1. Definitions.
|
8 |
+
|
9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
11 |
+
|
12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13 |
+
the copyright owner that is granting the License.
|
14 |
+
|
15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
16 |
+
other entities that control, are controlled by, or are under common
|
17 |
+
control with that entity. For the purposes of this definition,
|
18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
19 |
+
direction or management of such entity, whether by contract or
|
20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22 |
+
|
23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24 |
+
exercising permissions granted by this License.
|
25 |
+
|
26 |
+
"Source" form shall mean the preferred form for making modifications,
|
27 |
+
including but not limited to software source code, documentation
|
28 |
+
source, and configuration files.
|
29 |
+
|
30 |
+
"Object" form shall mean any form resulting from mechanical
|
31 |
+
transformation or translation of a Source form, including but
|
32 |
+
not limited to compiled object code, generated documentation,
|
33 |
+
and conversions to other media types.
|
34 |
+
|
35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
36 |
+
Object form, made available under the License, as indicated by a
|
37 |
+
copyright notice that is included in or attached to the work
|
38 |
+
(an example is provided in the Appendix below).
|
39 |
+
|
40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41 |
+
form, that is based on (or derived from) the Work and for which the
|
42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
44 |
+
of this License, Derivative Works shall not include works that remain
|
45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46 |
+
the Work and Derivative Works thereof.
|
47 |
+
|
48 |
+
"Contribution" shall mean any work of authorship, including
|
49 |
+
the original version of the Work and any modifications or additions
|
50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
54 |
+
means any form of electronic, verbal, or written communication sent
|
55 |
+
to the Licensor or its representatives, including but not limited to
|
56 |
+
communication on electronic mailing lists, source code control systems,
|
57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
59 |
+
excluding communication that is conspicuously marked or otherwise
|
60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
61 |
+
|
62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
64 |
+
subsequently incorporated within the Work.
|
65 |
+
|
66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
71 |
+
Work and such Derivative Works in Source or Object form.
|
72 |
+
|
73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76 |
+
(except as stated in this section) patent license to make, have made,
|
77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78 |
+
where such license applies only to those patent claims licensable
|
79 |
+
by such Contributor that are necessarily infringed by their
|
80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
82 |
+
institute patent litigation against any entity (including a
|
83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84 |
+
or a Contribution incorporated within the Work constitutes direct
|
85 |
+
or contributory patent infringement, then any patent licenses
|
86 |
+
granted to You under this License for that Work shall terminate
|
87 |
+
as of the date such litigation is filed.
|
88 |
+
|
89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
90 |
+
Work or Derivative Works thereof in any medium, with or without
|
91 |
+
modifications, and in Source or Object form, provided that You
|
92 |
+
meet the following conditions:
|
93 |
+
|
94 |
+
(a) You must give any other recipients of the Work or
|
95 |
+
Derivative Works a copy of this License; and
|
96 |
+
|
97 |
+
(b) You must cause any modified files to carry prominent notices
|
98 |
+
stating that You changed the files; and
|
99 |
+
|
100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
101 |
+
that You distribute, all copyright, patent, trademark, and
|
102 |
+
attribution notices from the Source form of the Work,
|
103 |
+
excluding those notices that do not pertain to any part of
|
104 |
+
the Derivative Works; and
|
105 |
+
|
106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107 |
+
distribution, then any Derivative Works that You distribute must
|
108 |
+
include a readable copy of the attribution notices contained
|
109 |
+
within such NOTICE file, excluding those notices that do not
|
110 |
+
pertain to any part of the Derivative Works, in at least one
|
111 |
+
of the following places: within a NOTICE text file distributed
|
112 |
+
as part of the Derivative Works; within the Source form or
|
113 |
+
documentation, if provided along with the Derivative Works; or,
|
114 |
+
within a display generated by the Derivative Works, if and
|
115 |
+
wherever such third-party notices normally appear. The contents
|
116 |
+
of the NOTICE file are for informational purposes only and
|
117 |
+
do not modify the License. You may add Your own attribution
|
118 |
+
notices within Derivative Works that You distribute, alongside
|
119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
120 |
+
that such additional attribution notices cannot be construed
|
121 |
+
as modifying the License.
|
122 |
+
|
123 |
+
You may add Your own copyright statement to Your modifications and
|
124 |
+
may provide additional or different license terms and conditions
|
125 |
+
for use, reproduction, or distribution of Your modifications, or
|
126 |
+
for any such Derivative Works as a whole, provided Your use,
|
127 |
+
reproduction, and distribution of the Work otherwise complies with
|
128 |
+
the conditions stated in this License.
|
129 |
+
|
130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
132 |
+
by You to the Licensor shall be under the terms and conditions of
|
133 |
+
this License, without any additional terms or conditions.
|
134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135 |
+
the terms of any separate license agreement you may have executed
|
136 |
+
with Licensor regarding such Contributions.
|
137 |
+
|
138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
140 |
+
except as required for reasonable and customary use in describing the
|
141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
142 |
+
|
143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144 |
+
agreed to in writing, Licensor provides the Work (and each
|
145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147 |
+
implied, including, without limitation, any warranties or conditions
|
148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150 |
+
appropriateness of using or redistributing the Work and assume any
|
151 |
+
risks associated with Your exercise of permissions under this License.
|
152 |
+
|
153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
154 |
+
whether in tort (including negligence), contract, or otherwise,
|
155 |
+
unless required by applicable law (such as deliberate and grossly
|
156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157 |
+
liable to You for damages, including any direct, indirect, special,
|
158 |
+
incidental, or consequential damages of any character arising as a
|
159 |
+
result of this License or out of the use or inability to use the
|
160 |
+
Work (including but not limited to damages for loss of goodwill,
|
161 |
+
work stoppage, computer failure or malfunction, or any and all
|
162 |
+
other commercial damages or losses), even if such Contributor
|
163 |
+
has been advised of the possibility of such damages.
|
164 |
+
|
165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168 |
+
or other liability obligations and/or rights consistent with this
|
169 |
+
License. However, in accepting such obligations, You may act only
|
170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171 |
+
of any other Contributor, and only if You agree to indemnify,
|
172 |
+
defend, and hold each Contributor harmless for any liability
|
173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
174 |
+
of your accepting any such warranty or additional liability.
|
175 |
+
|
176 |
+
END OF TERMS AND CONDITIONS
|
177 |
+
|
178 |
+
APPENDIX: How to apply the Apache License to your work.
|
179 |
+
|
180 |
+
To apply the Apache License to your work, attach the following
|
181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
182 |
+
replaced with your own identifying information. (Don't include
|
183 |
+
the brackets!) The text should be enclosed in the appropriate
|
184 |
+
comment syntax for the file format. We also recommend that a
|
185 |
+
file or class name and description of purpose be included on the
|
186 |
+
same "printed page" as the copyright notice for easier
|
187 |
+
identification within third-party archives.
|
188 |
+
|
189 |
+
Copyright [yyyy] [name of copyright owner]
|
190 |
+
|
191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192 |
+
you may not use this file except in compliance with the License.
|
193 |
+
You may obtain a copy of the License at
|
194 |
+
|
195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
196 |
+
|
197 |
+
Unless required by applicable law or agreed to in writing, software
|
198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200 |
+
See the License for the specific language governing permissions and
|
201 |
+
limitations under the License.
|
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: ControlNet
|
3 |
+
emoji: 🌖
|
4 |
+
colorFrom: pink
|
5 |
+
colorTo: blue
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 3.18.0
|
8 |
+
python_version: 3.10.9
|
9 |
+
app_file: app.py
|
10 |
+
pinned: false
|
11 |
+
duplicated_from: hysts/ControlNet
|
12 |
+
---
|
13 |
+
|
14 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
|
3 |
+
from __future__ import annotations
|
4 |
+
|
5 |
+
import os
|
6 |
+
import shlex
|
7 |
+
import subprocess
|
8 |
+
|
9 |
+
import gradio as gr
|
10 |
+
|
11 |
+
if os.getenv('SYSTEM') == 'spaces':
|
12 |
+
with open('patch') as f:
|
13 |
+
subprocess.run(shlex.split('patch -p1'), stdin=f, cwd='ControlNet')
|
14 |
+
commands = [
|
15 |
+
'wget https://huggingface.co/ckpt/ControlNet/resolve/main/dpt_hybrid-midas-501f0c75.pt -O dpt_hybrid-midas-501f0c75.pt',
|
16 |
+
'wget https://huggingface.co/ckpt/ControlNet/resolve/main/body_pose_model.pth -O body_pose_model.pth',
|
17 |
+
'wget https://huggingface.co/ckpt/ControlNet/resolve/main/hand_pose_model.pth -O hand_pose_model.pth',
|
18 |
+
'wget https://huggingface.co/ckpt/ControlNet/resolve/main/mlsd_large_512_fp32.pth -O mlsd_large_512_fp32.pth',
|
19 |
+
'wget https://huggingface.co/ckpt/ControlNet/resolve/main/mlsd_tiny_512_fp32.pth -O mlsd_tiny_512_fp32.pth',
|
20 |
+
'wget https://huggingface.co/ckpt/ControlNet/resolve/main/network-bsds500.pth -O network-bsds500.pth',
|
21 |
+
'wget https://huggingface.co/ckpt/ControlNet/resolve/main/upernet_global_small.pth -O upernet_global_small.pth',
|
22 |
+
]
|
23 |
+
for command in commands:
|
24 |
+
subprocess.run(shlex.split(command), cwd='ControlNet/annotator/ckpts/')
|
25 |
+
|
26 |
+
from gradio_canny2image import create_demo as create_demo_canny
|
27 |
+
from gradio_depth2image import create_demo as create_demo_depth
|
28 |
+
from gradio_fake_scribble2image import create_demo as create_demo_fake_scribble
|
29 |
+
from gradio_hed2image import create_demo as create_demo_hed
|
30 |
+
from gradio_hough2image import create_demo as create_demo_hough
|
31 |
+
from gradio_normal2image import create_demo as create_demo_normal
|
32 |
+
from gradio_pose2image import create_demo as create_demo_pose
|
33 |
+
from gradio_scribble2image import create_demo as create_demo_scribble
|
34 |
+
from gradio_scribble2image_interactive import \
|
35 |
+
create_demo as create_demo_scribble_interactive
|
36 |
+
from gradio_seg2image import create_demo as create_demo_seg
|
37 |
+
from model import Model
|
38 |
+
|
39 |
+
DESCRIPTION = '''# ControlNet
|
40 |
+
|
41 |
+
This is an unofficial demo for [https://github.com/lllyasviel/ControlNet](https://github.com/lllyasviel/ControlNet).
|
42 |
+
'''
|
43 |
+
if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
|
44 |
+
DESCRIPTION += f'''<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings.<br/>
|
45 |
+
<a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true">
|
46 |
+
<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
|
47 |
+
<p/>
|
48 |
+
'''
|
49 |
+
|
50 |
+
model = Model()
|
51 |
+
|
52 |
+
with gr.Blocks(css='style.css') as demo:
|
53 |
+
gr.Markdown(DESCRIPTION)
|
54 |
+
with gr.Tabs():
|
55 |
+
with gr.TabItem('Canny'):
|
56 |
+
create_demo_canny(model.process_canny)
|
57 |
+
with gr.TabItem('Hough'):
|
58 |
+
create_demo_hough(model.process_hough)
|
59 |
+
with gr.TabItem('HED'):
|
60 |
+
create_demo_hed(model.process_hed)
|
61 |
+
with gr.TabItem('Scribble'):
|
62 |
+
create_demo_scribble(model.process_scribble)
|
63 |
+
with gr.TabItem('Scribble Interactive'):
|
64 |
+
create_demo_scribble_interactive(
|
65 |
+
model.process_scribble_interactive)
|
66 |
+
with gr.TabItem('Fake Scribble'):
|
67 |
+
create_demo_fake_scribble(model.process_fake_scribble)
|
68 |
+
with gr.TabItem('Pose'):
|
69 |
+
create_demo_pose(model.process_pose)
|
70 |
+
with gr.TabItem('Segmentation'):
|
71 |
+
create_demo_seg(model.process_seg)
|
72 |
+
with gr.TabItem('Depth'):
|
73 |
+
create_demo_depth(model.process_depth)
|
74 |
+
with gr.TabItem('Normal map'):
|
75 |
+
create_demo_normal(model.process_normal)
|
76 |
+
|
77 |
+
demo.queue(api_open=False).launch()
|
gradio_canny2image.py
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_canny2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Canny Edge Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
low_threshold = gr.Slider(label='Canny low threshold',
|
27 |
+
minimum=1,
|
28 |
+
maximum=255,
|
29 |
+
value=100,
|
30 |
+
step=1)
|
31 |
+
high_threshold = gr.Slider(label='Canny high threshold',
|
32 |
+
minimum=1,
|
33 |
+
maximum=255,
|
34 |
+
value=200,
|
35 |
+
step=1)
|
36 |
+
ddim_steps = gr.Slider(label='Steps',
|
37 |
+
minimum=1,
|
38 |
+
maximum=100,
|
39 |
+
value=20,
|
40 |
+
step=1)
|
41 |
+
scale = gr.Slider(label='Guidance Scale',
|
42 |
+
minimum=0.1,
|
43 |
+
maximum=30.0,
|
44 |
+
value=9.0,
|
45 |
+
step=0.1)
|
46 |
+
seed = gr.Slider(label='Seed',
|
47 |
+
minimum=-1,
|
48 |
+
maximum=2147483647,
|
49 |
+
step=1,
|
50 |
+
randomize=True)
|
51 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
52 |
+
a_prompt = gr.Textbox(
|
53 |
+
label='Added Prompt',
|
54 |
+
value='best quality, extremely detailed')
|
55 |
+
n_prompt = gr.Textbox(
|
56 |
+
label='Negative Prompt',
|
57 |
+
value=
|
58 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
59 |
+
)
|
60 |
+
with gr.Column():
|
61 |
+
result_gallery = gr.Gallery(label='Output',
|
62 |
+
show_label=False,
|
63 |
+
elem_id='gallery').style(
|
64 |
+
grid=2, height='auto')
|
65 |
+
ips = [
|
66 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
67 |
+
image_resolution, ddim_steps, scale, seed, eta, low_threshold,
|
68 |
+
high_threshold
|
69 |
+
]
|
70 |
+
run_button.click(fn=process,
|
71 |
+
inputs=ips,
|
72 |
+
outputs=[result_gallery],
|
73 |
+
api_name='canny')
|
74 |
+
return demo
|
gradio_depth2image.py
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_depth2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Depth Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
detect_resolution = gr.Slider(label='Depth Resolution',
|
27 |
+
minimum=128,
|
28 |
+
maximum=1024,
|
29 |
+
value=384,
|
30 |
+
step=1)
|
31 |
+
ddim_steps = gr.Slider(label='Steps',
|
32 |
+
minimum=1,
|
33 |
+
maximum=100,
|
34 |
+
value=20,
|
35 |
+
step=1)
|
36 |
+
scale = gr.Slider(label='Guidance Scale',
|
37 |
+
minimum=0.1,
|
38 |
+
maximum=30.0,
|
39 |
+
value=9.0,
|
40 |
+
step=0.1)
|
41 |
+
seed = gr.Slider(label='Seed',
|
42 |
+
minimum=-1,
|
43 |
+
maximum=2147483647,
|
44 |
+
step=1,
|
45 |
+
randomize=True)
|
46 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
47 |
+
a_prompt = gr.Textbox(
|
48 |
+
label='Added Prompt',
|
49 |
+
value='best quality, extremely detailed')
|
50 |
+
n_prompt = gr.Textbox(
|
51 |
+
label='Negative Prompt',
|
52 |
+
value=
|
53 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
54 |
+
)
|
55 |
+
with gr.Column():
|
56 |
+
result_gallery = gr.Gallery(label='Output',
|
57 |
+
show_label=False,
|
58 |
+
elem_id='gallery').style(
|
59 |
+
grid=2, height='auto')
|
60 |
+
ips = [
|
61 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
62 |
+
image_resolution, detect_resolution, ddim_steps, scale, seed, eta
|
63 |
+
]
|
64 |
+
run_button.click(fn=process,
|
65 |
+
inputs=ips,
|
66 |
+
outputs=[result_gallery],
|
67 |
+
api_name='depth')
|
68 |
+
return demo
|
gradio_fake_scribble2image.py
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_fake_scribble2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Fake Scribble Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
detect_resolution = gr.Slider(label='HED Resolution',
|
27 |
+
minimum=128,
|
28 |
+
maximum=1024,
|
29 |
+
value=512,
|
30 |
+
step=1)
|
31 |
+
ddim_steps = gr.Slider(label='Steps',
|
32 |
+
minimum=1,
|
33 |
+
maximum=100,
|
34 |
+
value=20,
|
35 |
+
step=1)
|
36 |
+
scale = gr.Slider(label='Guidance Scale',
|
37 |
+
minimum=0.1,
|
38 |
+
maximum=30.0,
|
39 |
+
value=9.0,
|
40 |
+
step=0.1)
|
41 |
+
seed = gr.Slider(label='Seed',
|
42 |
+
minimum=-1,
|
43 |
+
maximum=2147483647,
|
44 |
+
step=1,
|
45 |
+
randomize=True)
|
46 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
47 |
+
a_prompt = gr.Textbox(
|
48 |
+
label='Added Prompt',
|
49 |
+
value='best quality, extremely detailed')
|
50 |
+
n_prompt = gr.Textbox(
|
51 |
+
label='Negative Prompt',
|
52 |
+
value=
|
53 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
54 |
+
)
|
55 |
+
with gr.Column():
|
56 |
+
result_gallery = gr.Gallery(label='Output',
|
57 |
+
show_label=False,
|
58 |
+
elem_id='gallery').style(
|
59 |
+
grid=2, height='auto')
|
60 |
+
ips = [
|
61 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
62 |
+
image_resolution, detect_resolution, ddim_steps, scale, seed, eta
|
63 |
+
]
|
64 |
+
run_button.click(fn=process,
|
65 |
+
inputs=ips,
|
66 |
+
outputs=[result_gallery],
|
67 |
+
api_name='fake_scribble')
|
68 |
+
return demo
|
gradio_hed2image.py
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_hed2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with HED Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
detect_resolution = gr.Slider(label='HED Resolution',
|
27 |
+
minimum=128,
|
28 |
+
maximum=1024,
|
29 |
+
value=512,
|
30 |
+
step=1)
|
31 |
+
ddim_steps = gr.Slider(label='Steps',
|
32 |
+
minimum=1,
|
33 |
+
maximum=100,
|
34 |
+
value=20,
|
35 |
+
step=1)
|
36 |
+
scale = gr.Slider(label='Guidance Scale',
|
37 |
+
minimum=0.1,
|
38 |
+
maximum=30.0,
|
39 |
+
value=9.0,
|
40 |
+
step=0.1)
|
41 |
+
seed = gr.Slider(label='Seed',
|
42 |
+
minimum=-1,
|
43 |
+
maximum=2147483647,
|
44 |
+
step=1,
|
45 |
+
randomize=True)
|
46 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
47 |
+
a_prompt = gr.Textbox(
|
48 |
+
label='Added Prompt',
|
49 |
+
value='best quality, extremely detailed')
|
50 |
+
n_prompt = gr.Textbox(
|
51 |
+
label='Negative Prompt',
|
52 |
+
value=
|
53 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
54 |
+
)
|
55 |
+
with gr.Column():
|
56 |
+
result_gallery = gr.Gallery(label='Output',
|
57 |
+
show_label=False,
|
58 |
+
elem_id='gallery').style(
|
59 |
+
grid=2, height='auto')
|
60 |
+
ips = [
|
61 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
62 |
+
image_resolution, detect_resolution, ddim_steps, scale, seed, eta
|
63 |
+
]
|
64 |
+
run_button.click(fn=process,
|
65 |
+
inputs=ips,
|
66 |
+
outputs=[result_gallery],
|
67 |
+
api_name='hed')
|
68 |
+
return demo
|
gradio_hough2image.py
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_hough2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Hough Line Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
detect_resolution = gr.Slider(label='Hough Resolution',
|
27 |
+
minimum=128,
|
28 |
+
maximum=1024,
|
29 |
+
value=512,
|
30 |
+
step=1)
|
31 |
+
value_threshold = gr.Slider(
|
32 |
+
label='Hough value threshold (MLSD)',
|
33 |
+
minimum=0.01,
|
34 |
+
maximum=2.0,
|
35 |
+
value=0.1,
|
36 |
+
step=0.01)
|
37 |
+
distance_threshold = gr.Slider(
|
38 |
+
label='Hough distance threshold (MLSD)',
|
39 |
+
minimum=0.01,
|
40 |
+
maximum=20.0,
|
41 |
+
value=0.1,
|
42 |
+
step=0.01)
|
43 |
+
ddim_steps = gr.Slider(label='Steps',
|
44 |
+
minimum=1,
|
45 |
+
maximum=100,
|
46 |
+
value=20,
|
47 |
+
step=1)
|
48 |
+
scale = gr.Slider(label='Guidance Scale',
|
49 |
+
minimum=0.1,
|
50 |
+
maximum=30.0,
|
51 |
+
value=9.0,
|
52 |
+
step=0.1)
|
53 |
+
seed = gr.Slider(label='Seed',
|
54 |
+
minimum=-1,
|
55 |
+
maximum=2147483647,
|
56 |
+
step=1,
|
57 |
+
randomize=True)
|
58 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
59 |
+
a_prompt = gr.Textbox(
|
60 |
+
label='Added Prompt',
|
61 |
+
value='best quality, extremely detailed')
|
62 |
+
n_prompt = gr.Textbox(
|
63 |
+
label='Negative Prompt',
|
64 |
+
value=
|
65 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
66 |
+
)
|
67 |
+
with gr.Column():
|
68 |
+
result_gallery = gr.Gallery(label='Output',
|
69 |
+
show_label=False,
|
70 |
+
elem_id='gallery').style(
|
71 |
+
grid=2, height='auto')
|
72 |
+
ips = [
|
73 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
74 |
+
image_resolution, detect_resolution, ddim_steps, scale, seed, eta,
|
75 |
+
value_threshold, distance_threshold
|
76 |
+
]
|
77 |
+
run_button.click(fn=process,
|
78 |
+
inputs=ips,
|
79 |
+
outputs=[result_gallery],
|
80 |
+
api_name='hough')
|
81 |
+
return demo
|
gradio_normal2image.py
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_normal2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Normal Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
detect_resolution = gr.Slider(label='Normal Resolution',
|
27 |
+
minimum=128,
|
28 |
+
maximum=1024,
|
29 |
+
value=384,
|
30 |
+
step=1)
|
31 |
+
bg_threshold = gr.Slider(
|
32 |
+
label='Normal background threshold',
|
33 |
+
minimum=0.0,
|
34 |
+
maximum=1.0,
|
35 |
+
value=0.4,
|
36 |
+
step=0.01)
|
37 |
+
ddim_steps = gr.Slider(label='Steps',
|
38 |
+
minimum=1,
|
39 |
+
maximum=100,
|
40 |
+
value=20,
|
41 |
+
step=1)
|
42 |
+
scale = gr.Slider(label='Guidance Scale',
|
43 |
+
minimum=0.1,
|
44 |
+
maximum=30.0,
|
45 |
+
value=9.0,
|
46 |
+
step=0.1)
|
47 |
+
seed = gr.Slider(label='Seed',
|
48 |
+
minimum=-1,
|
49 |
+
maximum=2147483647,
|
50 |
+
step=1,
|
51 |
+
randomize=True)
|
52 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
53 |
+
a_prompt = gr.Textbox(
|
54 |
+
label='Added Prompt',
|
55 |
+
value='best quality, extremely detailed')
|
56 |
+
n_prompt = gr.Textbox(
|
57 |
+
label='Negative Prompt',
|
58 |
+
value=
|
59 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
60 |
+
)
|
61 |
+
with gr.Column():
|
62 |
+
result_gallery = gr.Gallery(label='Output',
|
63 |
+
show_label=False,
|
64 |
+
elem_id='gallery').style(
|
65 |
+
grid=2, height='auto')
|
66 |
+
ips = [
|
67 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
68 |
+
image_resolution, detect_resolution, ddim_steps, scale, seed, eta,
|
69 |
+
bg_threshold
|
70 |
+
]
|
71 |
+
run_button.click(fn=process,
|
72 |
+
inputs=ips,
|
73 |
+
outputs=[result_gallery],
|
74 |
+
api_name='normal')
|
75 |
+
return demo
|
gradio_pose2image.py
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_pose2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Human Pose')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
detect_resolution = gr.Slider(label='OpenPose Resolution',
|
27 |
+
minimum=128,
|
28 |
+
maximum=1024,
|
29 |
+
value=512,
|
30 |
+
step=1)
|
31 |
+
ddim_steps = gr.Slider(label='Steps',
|
32 |
+
minimum=1,
|
33 |
+
maximum=100,
|
34 |
+
value=20,
|
35 |
+
step=1)
|
36 |
+
scale = gr.Slider(label='Guidance Scale',
|
37 |
+
minimum=0.1,
|
38 |
+
maximum=30.0,
|
39 |
+
value=9.0,
|
40 |
+
step=0.1)
|
41 |
+
seed = gr.Slider(label='Seed',
|
42 |
+
minimum=-1,
|
43 |
+
maximum=2147483647,
|
44 |
+
step=1,
|
45 |
+
randomize=True)
|
46 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
47 |
+
a_prompt = gr.Textbox(
|
48 |
+
label='Added Prompt',
|
49 |
+
value='best quality, extremely detailed')
|
50 |
+
n_prompt = gr.Textbox(
|
51 |
+
label='Negative Prompt',
|
52 |
+
value=
|
53 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
54 |
+
)
|
55 |
+
with gr.Column():
|
56 |
+
result_gallery = gr.Gallery(label='Output',
|
57 |
+
show_label=False,
|
58 |
+
elem_id='gallery').style(
|
59 |
+
grid=2, height='auto')
|
60 |
+
ips = [
|
61 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
62 |
+
image_resolution, detect_resolution, ddim_steps, scale, seed, eta
|
63 |
+
]
|
64 |
+
run_button.click(fn=process,
|
65 |
+
inputs=ips,
|
66 |
+
outputs=[result_gallery],
|
67 |
+
api_name='pose')
|
68 |
+
return demo
|
gradio_scribble2image.py
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_scribble2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Scribble Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
ddim_steps = gr.Slider(label='Steps',
|
27 |
+
minimum=1,
|
28 |
+
maximum=100,
|
29 |
+
value=20,
|
30 |
+
step=1)
|
31 |
+
scale = gr.Slider(label='Guidance Scale',
|
32 |
+
minimum=0.1,
|
33 |
+
maximum=30.0,
|
34 |
+
value=9.0,
|
35 |
+
step=0.1)
|
36 |
+
seed = gr.Slider(label='Seed',
|
37 |
+
minimum=-1,
|
38 |
+
maximum=2147483647,
|
39 |
+
step=1,
|
40 |
+
randomize=True)
|
41 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
42 |
+
a_prompt = gr.Textbox(
|
43 |
+
label='Added Prompt',
|
44 |
+
value='best quality, extremely detailed')
|
45 |
+
n_prompt = gr.Textbox(
|
46 |
+
label='Negative Prompt',
|
47 |
+
value=
|
48 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
49 |
+
)
|
50 |
+
with gr.Column():
|
51 |
+
result_gallery = gr.Gallery(label='Output',
|
52 |
+
show_label=False,
|
53 |
+
elem_id='gallery').style(
|
54 |
+
grid=2, height='auto')
|
55 |
+
ips = [
|
56 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
57 |
+
image_resolution, ddim_steps, scale, seed, eta
|
58 |
+
]
|
59 |
+
run_button.click(fn=process,
|
60 |
+
inputs=ips,
|
61 |
+
outputs=[result_gallery],
|
62 |
+
api_name='scribble')
|
63 |
+
return demo
|
gradio_scribble2image_interactive.py
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_scribble2image_interactive.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
import numpy as np
|
5 |
+
|
6 |
+
|
7 |
+
def create_canvas(w, h):
|
8 |
+
return np.zeros(shape=(h, w, 3), dtype=np.uint8) + 255
|
9 |
+
|
10 |
+
|
11 |
+
def create_demo(process):
|
12 |
+
with gr.Blocks() as demo:
|
13 |
+
with gr.Row():
|
14 |
+
gr.Markdown(
|
15 |
+
'## Control Stable Diffusion with Interactive Scribbles')
|
16 |
+
with gr.Row():
|
17 |
+
with gr.Column():
|
18 |
+
canvas_width = gr.Slider(label='Canvas Width',
|
19 |
+
minimum=256,
|
20 |
+
maximum=1024,
|
21 |
+
value=512,
|
22 |
+
step=1)
|
23 |
+
canvas_height = gr.Slider(label='Canvas Height',
|
24 |
+
minimum=256,
|
25 |
+
maximum=1024,
|
26 |
+
value=512,
|
27 |
+
step=1)
|
28 |
+
create_button = gr.Button(label='Start',
|
29 |
+
value='Open drawing canvas!')
|
30 |
+
input_image = gr.Image(source='upload',
|
31 |
+
type='numpy',
|
32 |
+
tool='sketch')
|
33 |
+
gr.Markdown(
|
34 |
+
value=
|
35 |
+
'Do not forget to change your brush width to make it thinner. (Gradio do not allow developers to set brush width so you need to do it manually.) '
|
36 |
+
'Just click on the small pencil icon in the upper right corner of the above block.'
|
37 |
+
)
|
38 |
+
create_button.click(fn=create_canvas,
|
39 |
+
inputs=[canvas_width, canvas_height],
|
40 |
+
outputs=[input_image])
|
41 |
+
prompt = gr.Textbox(label='Prompt')
|
42 |
+
run_button = gr.Button(label='Run')
|
43 |
+
with gr.Accordion('Advanced options', open=False):
|
44 |
+
num_samples = gr.Slider(label='Images',
|
45 |
+
minimum=1,
|
46 |
+
maximum=12,
|
47 |
+
value=1,
|
48 |
+
step=1)
|
49 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
50 |
+
minimum=256,
|
51 |
+
maximum=768,
|
52 |
+
value=512,
|
53 |
+
step=256)
|
54 |
+
ddim_steps = gr.Slider(label='Steps',
|
55 |
+
minimum=1,
|
56 |
+
maximum=100,
|
57 |
+
value=20,
|
58 |
+
step=1)
|
59 |
+
scale = gr.Slider(label='Guidance Scale',
|
60 |
+
minimum=0.1,
|
61 |
+
maximum=30.0,
|
62 |
+
value=9.0,
|
63 |
+
step=0.1)
|
64 |
+
seed = gr.Slider(label='Seed',
|
65 |
+
minimum=-1,
|
66 |
+
maximum=2147483647,
|
67 |
+
step=1,
|
68 |
+
randomize=True)
|
69 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
70 |
+
a_prompt = gr.Textbox(
|
71 |
+
label='Added Prompt',
|
72 |
+
value='best quality, extremely detailed')
|
73 |
+
n_prompt = gr.Textbox(
|
74 |
+
label='Negative Prompt',
|
75 |
+
value=
|
76 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
77 |
+
)
|
78 |
+
with gr.Column():
|
79 |
+
result_gallery = gr.Gallery(label='Output',
|
80 |
+
show_label=False,
|
81 |
+
elem_id='gallery').style(
|
82 |
+
grid=2, height='auto')
|
83 |
+
ips = [
|
84 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
85 |
+
image_resolution, ddim_steps, scale, seed, eta
|
86 |
+
]
|
87 |
+
run_button.click(fn=process, inputs=ips, outputs=[result_gallery])
|
88 |
+
return demo
|
gradio_seg2image.py
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_seg2image.py
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
import gradio as gr
|
4 |
+
|
5 |
+
|
6 |
+
def create_demo(process):
|
7 |
+
with gr.Blocks() as demo:
|
8 |
+
with gr.Row():
|
9 |
+
gr.Markdown('## Control Stable Diffusion with Segmentation Maps')
|
10 |
+
with gr.Row():
|
11 |
+
with gr.Column():
|
12 |
+
input_image = gr.Image(source='upload', type='numpy')
|
13 |
+
prompt = gr.Textbox(label='Prompt')
|
14 |
+
run_button = gr.Button(label='Run')
|
15 |
+
with gr.Accordion('Advanced options', open=False):
|
16 |
+
num_samples = gr.Slider(label='Images',
|
17 |
+
minimum=1,
|
18 |
+
maximum=12,
|
19 |
+
value=1,
|
20 |
+
step=1)
|
21 |
+
image_resolution = gr.Slider(label='Image Resolution',
|
22 |
+
minimum=256,
|
23 |
+
maximum=768,
|
24 |
+
value=512,
|
25 |
+
step=256)
|
26 |
+
detect_resolution = gr.Slider(
|
27 |
+
label='Segmentation Resolution',
|
28 |
+
minimum=128,
|
29 |
+
maximum=1024,
|
30 |
+
value=512,
|
31 |
+
step=1)
|
32 |
+
ddim_steps = gr.Slider(label='Steps',
|
33 |
+
minimum=1,
|
34 |
+
maximum=100,
|
35 |
+
value=20,
|
36 |
+
step=1)
|
37 |
+
scale = gr.Slider(label='Guidance Scale',
|
38 |
+
minimum=0.1,
|
39 |
+
maximum=30.0,
|
40 |
+
value=9.0,
|
41 |
+
step=0.1)
|
42 |
+
seed = gr.Slider(label='Seed',
|
43 |
+
minimum=-1,
|
44 |
+
maximum=2147483647,
|
45 |
+
step=1,
|
46 |
+
randomize=True)
|
47 |
+
eta = gr.Number(label='eta (DDIM)', value=0.0)
|
48 |
+
a_prompt = gr.Textbox(
|
49 |
+
label='Added Prompt',
|
50 |
+
value='best quality, extremely detailed')
|
51 |
+
n_prompt = gr.Textbox(
|
52 |
+
label='Negative Prompt',
|
53 |
+
value=
|
54 |
+
'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
|
55 |
+
)
|
56 |
+
with gr.Column():
|
57 |
+
result_gallery = gr.Gallery(label='Output',
|
58 |
+
show_label=False,
|
59 |
+
elem_id='gallery').style(
|
60 |
+
grid=2, height='auto')
|
61 |
+
ips = [
|
62 |
+
input_image, prompt, a_prompt, n_prompt, num_samples,
|
63 |
+
image_resolution, detect_resolution, ddim_steps, scale, seed, eta
|
64 |
+
]
|
65 |
+
run_button.click(fn=process,
|
66 |
+
inputs=ips,
|
67 |
+
outputs=[result_gallery],
|
68 |
+
api_name='seg')
|
69 |
+
return demo
|
model.py
ADDED
@@ -0,0 +1,725 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file is adapted from gradio_*.py in https://github.com/lllyasviel/ControlNet/tree/f4748e3630d8141d7765e2bd9b1e348f47847707
|
2 |
+
# The original license file is LICENSE.ControlNet this repo.
|
3 |
+
from __future__ import annotations
|
4 |
+
|
5 |
+
import pathlib
|
6 |
+
import random
|
7 |
+
import shlex
|
8 |
+
import subprocess
|
9 |
+
import sys
|
10 |
+
|
11 |
+
import cv2
|
12 |
+
import einops
|
13 |
+
import numpy as np
|
14 |
+
import torch
|
15 |
+
from pytorch_lightning import seed_everything
|
16 |
+
|
17 |
+
sys.path.append('ControlNet')
|
18 |
+
|
19 |
+
import config
|
20 |
+
from annotator.canny import apply_canny
|
21 |
+
from annotator.hed import apply_hed, nms
|
22 |
+
from annotator.midas import apply_midas
|
23 |
+
from annotator.mlsd import apply_mlsd
|
24 |
+
from annotator.openpose import apply_openpose
|
25 |
+
from annotator.uniformer import apply_uniformer
|
26 |
+
from annotator.util import HWC3, resize_image
|
27 |
+
from cldm.model import create_model, load_state_dict
|
28 |
+
from ldm.models.diffusion.ddim import DDIMSampler
|
29 |
+
from share import *
|
30 |
+
|
31 |
+
|
32 |
+
class Model:
|
33 |
+
WEIGHT_NAMES = {
|
34 |
+
'canny': 'control_sd15_canny.pth',
|
35 |
+
'hough': 'control_sd15_mlsd.pth',
|
36 |
+
'hed': 'control_sd15_hed.pth',
|
37 |
+
'scribble': 'control_sd15_scribble.pth',
|
38 |
+
'pose': 'control_sd15_openpose.pth',
|
39 |
+
'seg': 'control_sd15_seg.pth',
|
40 |
+
'depth': 'control_sd15_depth.pth',
|
41 |
+
'normal': 'control_sd15_normal.pth',
|
42 |
+
}
|
43 |
+
|
44 |
+
def __init__(self,
|
45 |
+
model_config_path: str = 'ControlNet/models/cldm_v15.yaml',
|
46 |
+
model_dir: str = 'models'):
|
47 |
+
self.device = torch.device(
|
48 |
+
'cuda:0' if torch.cuda.is_available() else 'cpu')
|
49 |
+
self.model = create_model(model_config_path).to(self.device)
|
50 |
+
self.ddim_sampler = DDIMSampler(self.model)
|
51 |
+
self.task_name = ''
|
52 |
+
|
53 |
+
self.model_dir = pathlib.Path(model_dir)
|
54 |
+
self.download_models()
|
55 |
+
|
56 |
+
def load_weight(self, task_name: str) -> None:
|
57 |
+
if task_name == self.task_name:
|
58 |
+
return
|
59 |
+
weight_path = self.get_weight_path(task_name)
|
60 |
+
self.model.load_state_dict(
|
61 |
+
load_state_dict(weight_path, location=self.device))
|
62 |
+
self.task_name = task_name
|
63 |
+
|
64 |
+
def get_weight_path(self, task_name: str) -> str:
|
65 |
+
if 'scribble' in task_name:
|
66 |
+
task_name = 'scribble'
|
67 |
+
return f'{self.model_dir}/{self.WEIGHT_NAMES[task_name]}'
|
68 |
+
|
69 |
+
def download_models(self):
|
70 |
+
self.model_dir.mkdir(exist_ok=True, parents=True)
|
71 |
+
for name in self.WEIGHT_NAMES.values():
|
72 |
+
out_path = self.model_dir / name
|
73 |
+
if out_path.exists():
|
74 |
+
continue
|
75 |
+
subprocess.run(
|
76 |
+
shlex.split(
|
77 |
+
f'wget https://huggingface.co/ckpt/ControlNet/resolve/main/{name} -O {out_path}'
|
78 |
+
))
|
79 |
+
|
80 |
+
@torch.inference_mode()
|
81 |
+
def process_canny(self, input_image, prompt, a_prompt, n_prompt,
|
82 |
+
num_samples, image_resolution, ddim_steps, scale, seed,
|
83 |
+
eta, low_threshold, high_threshold):
|
84 |
+
self.load_weight('canny')
|
85 |
+
|
86 |
+
img = resize_image(HWC3(input_image), image_resolution)
|
87 |
+
H, W, C = img.shape
|
88 |
+
|
89 |
+
detected_map = apply_canny(img, low_threshold, high_threshold)
|
90 |
+
detected_map = HWC3(detected_map)
|
91 |
+
|
92 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
93 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
94 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
95 |
+
|
96 |
+
if seed == -1:
|
97 |
+
seed = random.randint(0, 65535)
|
98 |
+
seed_everything(seed)
|
99 |
+
|
100 |
+
if config.save_memory:
|
101 |
+
self.model.low_vram_shift(is_diffusing=False)
|
102 |
+
|
103 |
+
cond = {
|
104 |
+
'c_concat': [control],
|
105 |
+
'c_crossattn': [
|
106 |
+
self.model.get_learned_conditioning(
|
107 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
108 |
+
]
|
109 |
+
}
|
110 |
+
un_cond = {
|
111 |
+
'c_concat': [control],
|
112 |
+
'c_crossattn':
|
113 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
114 |
+
}
|
115 |
+
shape = (4, H // 8, W // 8)
|
116 |
+
|
117 |
+
if config.save_memory:
|
118 |
+
self.model.low_vram_shift(is_diffusing=True)
|
119 |
+
|
120 |
+
samples, intermediates = self.ddim_sampler.sample(
|
121 |
+
ddim_steps,
|
122 |
+
num_samples,
|
123 |
+
shape,
|
124 |
+
cond,
|
125 |
+
verbose=False,
|
126 |
+
eta=eta,
|
127 |
+
unconditional_guidance_scale=scale,
|
128 |
+
unconditional_conditioning=un_cond)
|
129 |
+
|
130 |
+
if config.save_memory:
|
131 |
+
self.model.low_vram_shift(is_diffusing=False)
|
132 |
+
|
133 |
+
x_samples = self.model.decode_first_stage(samples)
|
134 |
+
x_samples = (
|
135 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
136 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
137 |
+
|
138 |
+
results = [x_samples[i] for i in range(num_samples)]
|
139 |
+
return [255 - detected_map] + results
|
140 |
+
|
141 |
+
@torch.inference_mode()
|
142 |
+
def process_hough(self, input_image, prompt, a_prompt, n_prompt,
|
143 |
+
num_samples, image_resolution, detect_resolution,
|
144 |
+
ddim_steps, scale, seed, eta, value_threshold,
|
145 |
+
distance_threshold):
|
146 |
+
self.load_weight('hough')
|
147 |
+
|
148 |
+
input_image = HWC3(input_image)
|
149 |
+
detected_map = apply_mlsd(resize_image(input_image, detect_resolution),
|
150 |
+
value_threshold, distance_threshold)
|
151 |
+
detected_map = HWC3(detected_map)
|
152 |
+
img = resize_image(input_image, image_resolution)
|
153 |
+
H, W, C = img.shape
|
154 |
+
|
155 |
+
detected_map = cv2.resize(detected_map, (W, H),
|
156 |
+
interpolation=cv2.INTER_NEAREST)
|
157 |
+
|
158 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
159 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
160 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
161 |
+
|
162 |
+
if seed == -1:
|
163 |
+
seed = random.randint(0, 65535)
|
164 |
+
seed_everything(seed)
|
165 |
+
|
166 |
+
if config.save_memory:
|
167 |
+
self.model.low_vram_shift(is_diffusing=False)
|
168 |
+
|
169 |
+
cond = {
|
170 |
+
'c_concat': [control],
|
171 |
+
'c_crossattn': [
|
172 |
+
self.model.get_learned_conditioning(
|
173 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
174 |
+
]
|
175 |
+
}
|
176 |
+
un_cond = {
|
177 |
+
'c_concat': [control],
|
178 |
+
'c_crossattn':
|
179 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
180 |
+
}
|
181 |
+
shape = (4, H // 8, W // 8)
|
182 |
+
|
183 |
+
if config.save_memory:
|
184 |
+
self.model.low_vram_shift(is_diffusing=True)
|
185 |
+
|
186 |
+
samples, intermediates = self.ddim_sampler.sample(
|
187 |
+
ddim_steps,
|
188 |
+
num_samples,
|
189 |
+
shape,
|
190 |
+
cond,
|
191 |
+
verbose=False,
|
192 |
+
eta=eta,
|
193 |
+
unconditional_guidance_scale=scale,
|
194 |
+
unconditional_conditioning=un_cond)
|
195 |
+
|
196 |
+
if config.save_memory:
|
197 |
+
self.model.low_vram_shift(is_diffusing=False)
|
198 |
+
|
199 |
+
x_samples = self.model.decode_first_stage(samples)
|
200 |
+
x_samples = (
|
201 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
202 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
203 |
+
|
204 |
+
results = [x_samples[i] for i in range(num_samples)]
|
205 |
+
return [
|
206 |
+
255 - cv2.dilate(detected_map,
|
207 |
+
np.ones(shape=(3, 3), dtype=np.uint8),
|
208 |
+
iterations=1)
|
209 |
+
] + results
|
210 |
+
|
211 |
+
@torch.inference_mode()
|
212 |
+
def process_hed(self, input_image, prompt, a_prompt, n_prompt, num_samples,
|
213 |
+
image_resolution, detect_resolution, ddim_steps, scale,
|
214 |
+
seed, eta):
|
215 |
+
self.load_weight('hed')
|
216 |
+
|
217 |
+
input_image = HWC3(input_image)
|
218 |
+
detected_map = apply_hed(resize_image(input_image, detect_resolution))
|
219 |
+
detected_map = HWC3(detected_map)
|
220 |
+
img = resize_image(input_image, image_resolution)
|
221 |
+
H, W, C = img.shape
|
222 |
+
|
223 |
+
detected_map = cv2.resize(detected_map, (W, H),
|
224 |
+
interpolation=cv2.INTER_LINEAR)
|
225 |
+
|
226 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
227 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
228 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
229 |
+
|
230 |
+
if seed == -1:
|
231 |
+
seed = random.randint(0, 65535)
|
232 |
+
seed_everything(seed)
|
233 |
+
|
234 |
+
if config.save_memory:
|
235 |
+
self.model.low_vram_shift(is_diffusing=False)
|
236 |
+
|
237 |
+
cond = {
|
238 |
+
'c_concat': [control],
|
239 |
+
'c_crossattn': [
|
240 |
+
self.model.get_learned_conditioning(
|
241 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
242 |
+
]
|
243 |
+
}
|
244 |
+
un_cond = {
|
245 |
+
'c_concat': [control],
|
246 |
+
'c_crossattn':
|
247 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
248 |
+
}
|
249 |
+
shape = (4, H // 8, W // 8)
|
250 |
+
|
251 |
+
if config.save_memory:
|
252 |
+
self.model.low_vram_shift(is_diffusing=True)
|
253 |
+
|
254 |
+
samples, intermediates = self.ddim_sampler.sample(
|
255 |
+
ddim_steps,
|
256 |
+
num_samples,
|
257 |
+
shape,
|
258 |
+
cond,
|
259 |
+
verbose=False,
|
260 |
+
eta=eta,
|
261 |
+
unconditional_guidance_scale=scale,
|
262 |
+
unconditional_conditioning=un_cond)
|
263 |
+
|
264 |
+
if config.save_memory:
|
265 |
+
self.model.low_vram_shift(is_diffusing=False)
|
266 |
+
|
267 |
+
x_samples = self.model.decode_first_stage(samples)
|
268 |
+
x_samples = (
|
269 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
270 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
271 |
+
|
272 |
+
results = [x_samples[i] for i in range(num_samples)]
|
273 |
+
return [detected_map] + results
|
274 |
+
|
275 |
+
@torch.inference_mode()
|
276 |
+
def process_scribble(self, input_image, prompt, a_prompt, n_prompt,
|
277 |
+
num_samples, image_resolution, ddim_steps, scale,
|
278 |
+
seed, eta):
|
279 |
+
self.load_weight('scribble')
|
280 |
+
|
281 |
+
img = resize_image(HWC3(input_image), image_resolution)
|
282 |
+
H, W, C = img.shape
|
283 |
+
|
284 |
+
detected_map = np.zeros_like(img, dtype=np.uint8)
|
285 |
+
detected_map[np.min(img, axis=2) < 127] = 255
|
286 |
+
|
287 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
288 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
289 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
290 |
+
|
291 |
+
if seed == -1:
|
292 |
+
seed = random.randint(0, 65535)
|
293 |
+
seed_everything(seed)
|
294 |
+
|
295 |
+
if config.save_memory:
|
296 |
+
self.model.low_vram_shift(is_diffusing=False)
|
297 |
+
|
298 |
+
cond = {
|
299 |
+
'c_concat': [control],
|
300 |
+
'c_crossattn': [
|
301 |
+
self.model.get_learned_conditioning(
|
302 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
303 |
+
]
|
304 |
+
}
|
305 |
+
un_cond = {
|
306 |
+
'c_concat': [control],
|
307 |
+
'c_crossattn':
|
308 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
309 |
+
}
|
310 |
+
shape = (4, H // 8, W // 8)
|
311 |
+
|
312 |
+
if config.save_memory:
|
313 |
+
self.model.low_vram_shift(is_diffusing=True)
|
314 |
+
|
315 |
+
samples, intermediates = self.ddim_sampler.sample(
|
316 |
+
ddim_steps,
|
317 |
+
num_samples,
|
318 |
+
shape,
|
319 |
+
cond,
|
320 |
+
verbose=False,
|
321 |
+
eta=eta,
|
322 |
+
unconditional_guidance_scale=scale,
|
323 |
+
unconditional_conditioning=un_cond)
|
324 |
+
|
325 |
+
if config.save_memory:
|
326 |
+
self.model.low_vram_shift(is_diffusing=False)
|
327 |
+
|
328 |
+
x_samples = self.model.decode_first_stage(samples)
|
329 |
+
x_samples = (
|
330 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
331 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
332 |
+
|
333 |
+
results = [x_samples[i] for i in range(num_samples)]
|
334 |
+
return [255 - detected_map] + results
|
335 |
+
|
336 |
+
@torch.inference_mode()
|
337 |
+
def process_scribble_interactive(self, input_image, prompt, a_prompt,
|
338 |
+
n_prompt, num_samples, image_resolution,
|
339 |
+
ddim_steps, scale, seed, eta):
|
340 |
+
self.load_weight('scribble')
|
341 |
+
|
342 |
+
img = resize_image(HWC3(input_image['mask'][:, :, 0]),
|
343 |
+
image_resolution)
|
344 |
+
H, W, C = img.shape
|
345 |
+
|
346 |
+
detected_map = np.zeros_like(img, dtype=np.uint8)
|
347 |
+
detected_map[np.min(img, axis=2) > 127] = 255
|
348 |
+
|
349 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
350 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
351 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
352 |
+
|
353 |
+
if seed == -1:
|
354 |
+
seed = random.randint(0, 65535)
|
355 |
+
seed_everything(seed)
|
356 |
+
|
357 |
+
if config.save_memory:
|
358 |
+
self.model.low_vram_shift(is_diffusing=False)
|
359 |
+
|
360 |
+
cond = {
|
361 |
+
'c_concat': [control],
|
362 |
+
'c_crossattn': [
|
363 |
+
self.model.get_learned_conditioning(
|
364 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
365 |
+
]
|
366 |
+
}
|
367 |
+
un_cond = {
|
368 |
+
'c_concat': [control],
|
369 |
+
'c_crossattn':
|
370 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
371 |
+
}
|
372 |
+
shape = (4, H // 8, W // 8)
|
373 |
+
|
374 |
+
if config.save_memory:
|
375 |
+
self.model.low_vram_shift(is_diffusing=True)
|
376 |
+
|
377 |
+
samples, intermediates = self.ddim_sampler.sample(
|
378 |
+
ddim_steps,
|
379 |
+
num_samples,
|
380 |
+
shape,
|
381 |
+
cond,
|
382 |
+
verbose=False,
|
383 |
+
eta=eta,
|
384 |
+
unconditional_guidance_scale=scale,
|
385 |
+
unconditional_conditioning=un_cond)
|
386 |
+
|
387 |
+
if config.save_memory:
|
388 |
+
self.model.low_vram_shift(is_diffusing=False)
|
389 |
+
|
390 |
+
x_samples = self.model.decode_first_stage(samples)
|
391 |
+
x_samples = (
|
392 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
393 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
394 |
+
|
395 |
+
results = [x_samples[i] for i in range(num_samples)]
|
396 |
+
return [255 - detected_map] + results
|
397 |
+
|
398 |
+
@torch.inference_mode()
|
399 |
+
def process_fake_scribble(self, input_image, prompt, a_prompt, n_prompt,
|
400 |
+
num_samples, image_resolution, detect_resolution,
|
401 |
+
ddim_steps, scale, seed, eta):
|
402 |
+
self.load_weight('scribble')
|
403 |
+
|
404 |
+
input_image = HWC3(input_image)
|
405 |
+
detected_map = apply_hed(resize_image(input_image, detect_resolution))
|
406 |
+
detected_map = HWC3(detected_map)
|
407 |
+
img = resize_image(input_image, image_resolution)
|
408 |
+
H, W, C = img.shape
|
409 |
+
|
410 |
+
detected_map = cv2.resize(detected_map, (W, H),
|
411 |
+
interpolation=cv2.INTER_LINEAR)
|
412 |
+
detected_map = nms(detected_map, 127, 3.0)
|
413 |
+
detected_map = cv2.GaussianBlur(detected_map, (0, 0), 3.0)
|
414 |
+
detected_map[detected_map > 4] = 255
|
415 |
+
detected_map[detected_map < 255] = 0
|
416 |
+
|
417 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
418 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
419 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
420 |
+
|
421 |
+
if seed == -1:
|
422 |
+
seed = random.randint(0, 65535)
|
423 |
+
seed_everything(seed)
|
424 |
+
|
425 |
+
if config.save_memory:
|
426 |
+
self.model.low_vram_shift(is_diffusing=False)
|
427 |
+
|
428 |
+
cond = {
|
429 |
+
'c_concat': [control],
|
430 |
+
'c_crossattn': [
|
431 |
+
self.model.get_learned_conditioning(
|
432 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
433 |
+
]
|
434 |
+
}
|
435 |
+
un_cond = {
|
436 |
+
'c_concat': [control],
|
437 |
+
'c_crossattn':
|
438 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
439 |
+
}
|
440 |
+
shape = (4, H // 8, W // 8)
|
441 |
+
|
442 |
+
if config.save_memory:
|
443 |
+
self.model.low_vram_shift(is_diffusing=True)
|
444 |
+
|
445 |
+
samples, intermediates = self.ddim_sampler.sample(
|
446 |
+
ddim_steps,
|
447 |
+
num_samples,
|
448 |
+
shape,
|
449 |
+
cond,
|
450 |
+
verbose=False,
|
451 |
+
eta=eta,
|
452 |
+
unconditional_guidance_scale=scale,
|
453 |
+
unconditional_conditioning=un_cond)
|
454 |
+
|
455 |
+
if config.save_memory:
|
456 |
+
self.model.low_vram_shift(is_diffusing=False)
|
457 |
+
|
458 |
+
x_samples = self.model.decode_first_stage(samples)
|
459 |
+
x_samples = (
|
460 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
461 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
462 |
+
|
463 |
+
results = [x_samples[i] for i in range(num_samples)]
|
464 |
+
return [255 - detected_map] + results
|
465 |
+
|
466 |
+
@torch.inference_mode()
|
467 |
+
def process_pose(self, input_image, prompt, a_prompt, n_prompt,
|
468 |
+
num_samples, image_resolution, detect_resolution,
|
469 |
+
ddim_steps, scale, seed, eta):
|
470 |
+
self.load_weight('pose')
|
471 |
+
|
472 |
+
input_image = HWC3(input_image)
|
473 |
+
detected_map, _ = apply_openpose(
|
474 |
+
resize_image(input_image, detect_resolution))
|
475 |
+
detected_map = HWC3(detected_map)
|
476 |
+
img = resize_image(input_image, image_resolution)
|
477 |
+
H, W, C = img.shape
|
478 |
+
|
479 |
+
detected_map = cv2.resize(detected_map, (W, H),
|
480 |
+
interpolation=cv2.INTER_NEAREST)
|
481 |
+
|
482 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
483 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
484 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
485 |
+
|
486 |
+
if seed == -1:
|
487 |
+
seed = random.randint(0, 65535)
|
488 |
+
seed_everything(seed)
|
489 |
+
|
490 |
+
if config.save_memory:
|
491 |
+
self.model.low_vram_shift(is_diffusing=False)
|
492 |
+
|
493 |
+
cond = {
|
494 |
+
'c_concat': [control],
|
495 |
+
'c_crossattn': [
|
496 |
+
self.model.get_learned_conditioning(
|
497 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
498 |
+
]
|
499 |
+
}
|
500 |
+
un_cond = {
|
501 |
+
'c_concat': [control],
|
502 |
+
'c_crossattn':
|
503 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
504 |
+
}
|
505 |
+
shape = (4, H // 8, W // 8)
|
506 |
+
|
507 |
+
if config.save_memory:
|
508 |
+
self.model.low_vram_shift(is_diffusing=True)
|
509 |
+
|
510 |
+
samples, intermediates = self.ddim_sampler.sample(
|
511 |
+
ddim_steps,
|
512 |
+
num_samples,
|
513 |
+
shape,
|
514 |
+
cond,
|
515 |
+
verbose=False,
|
516 |
+
eta=eta,
|
517 |
+
unconditional_guidance_scale=scale,
|
518 |
+
unconditional_conditioning=un_cond)
|
519 |
+
|
520 |
+
if config.save_memory:
|
521 |
+
self.model.low_vram_shift(is_diffusing=False)
|
522 |
+
|
523 |
+
x_samples = self.model.decode_first_stage(samples)
|
524 |
+
x_samples = (
|
525 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
526 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
527 |
+
|
528 |
+
results = [x_samples[i] for i in range(num_samples)]
|
529 |
+
return [detected_map] + results
|
530 |
+
|
531 |
+
@torch.inference_mode()
|
532 |
+
def process_seg(self, input_image, prompt, a_prompt, n_prompt, num_samples,
|
533 |
+
image_resolution, detect_resolution, ddim_steps, scale,
|
534 |
+
seed, eta):
|
535 |
+
self.load_weight('seg')
|
536 |
+
|
537 |
+
input_image = HWC3(input_image)
|
538 |
+
detected_map = apply_uniformer(
|
539 |
+
resize_image(input_image, detect_resolution))
|
540 |
+
img = resize_image(input_image, image_resolution)
|
541 |
+
H, W, C = img.shape
|
542 |
+
|
543 |
+
detected_map = cv2.resize(detected_map, (W, H),
|
544 |
+
interpolation=cv2.INTER_NEAREST)
|
545 |
+
|
546 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
547 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
548 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
549 |
+
|
550 |
+
if seed == -1:
|
551 |
+
seed = random.randint(0, 65535)
|
552 |
+
seed_everything(seed)
|
553 |
+
|
554 |
+
if config.save_memory:
|
555 |
+
self.model.low_vram_shift(is_diffusing=False)
|
556 |
+
|
557 |
+
cond = {
|
558 |
+
'c_concat': [control],
|
559 |
+
'c_crossattn': [
|
560 |
+
self.model.get_learned_conditioning(
|
561 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
562 |
+
]
|
563 |
+
}
|
564 |
+
un_cond = {
|
565 |
+
'c_concat': [control],
|
566 |
+
'c_crossattn':
|
567 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
568 |
+
}
|
569 |
+
shape = (4, H // 8, W // 8)
|
570 |
+
|
571 |
+
if config.save_memory:
|
572 |
+
self.model.low_vram_shift(is_diffusing=True)
|
573 |
+
|
574 |
+
samples, intermediates = self.ddim_sampler.sample(
|
575 |
+
ddim_steps,
|
576 |
+
num_samples,
|
577 |
+
shape,
|
578 |
+
cond,
|
579 |
+
verbose=False,
|
580 |
+
eta=eta,
|
581 |
+
unconditional_guidance_scale=scale,
|
582 |
+
unconditional_conditioning=un_cond)
|
583 |
+
|
584 |
+
if config.save_memory:
|
585 |
+
self.model.low_vram_shift(is_diffusing=False)
|
586 |
+
|
587 |
+
x_samples = self.model.decode_first_stage(samples)
|
588 |
+
x_samples = (
|
589 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
590 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
591 |
+
|
592 |
+
results = [x_samples[i] for i in range(num_samples)]
|
593 |
+
return [detected_map] + results
|
594 |
+
|
595 |
+
@torch.inference_mode()
|
596 |
+
def process_depth(self, input_image, prompt, a_prompt, n_prompt,
|
597 |
+
num_samples, image_resolution, detect_resolution,
|
598 |
+
ddim_steps, scale, seed, eta):
|
599 |
+
self.load_weight('depth')
|
600 |
+
|
601 |
+
input_image = HWC3(input_image)
|
602 |
+
detected_map, _ = apply_midas(
|
603 |
+
resize_image(input_image, detect_resolution))
|
604 |
+
detected_map = HWC3(detected_map)
|
605 |
+
img = resize_image(input_image, image_resolution)
|
606 |
+
H, W, C = img.shape
|
607 |
+
|
608 |
+
detected_map = cv2.resize(detected_map, (W, H),
|
609 |
+
interpolation=cv2.INTER_LINEAR)
|
610 |
+
|
611 |
+
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
|
612 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
613 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
614 |
+
|
615 |
+
if seed == -1:
|
616 |
+
seed = random.randint(0, 65535)
|
617 |
+
seed_everything(seed)
|
618 |
+
|
619 |
+
if config.save_memory:
|
620 |
+
self.model.low_vram_shift(is_diffusing=False)
|
621 |
+
|
622 |
+
cond = {
|
623 |
+
'c_concat': [control],
|
624 |
+
'c_crossattn': [
|
625 |
+
self.model.get_learned_conditioning(
|
626 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
627 |
+
]
|
628 |
+
}
|
629 |
+
un_cond = {
|
630 |
+
'c_concat': [control],
|
631 |
+
'c_crossattn':
|
632 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
633 |
+
}
|
634 |
+
shape = (4, H // 8, W // 8)
|
635 |
+
|
636 |
+
if config.save_memory:
|
637 |
+
self.model.low_vram_shift(is_diffusing=True)
|
638 |
+
|
639 |
+
samples, intermediates = self.ddim_sampler.sample(
|
640 |
+
ddim_steps,
|
641 |
+
num_samples,
|
642 |
+
shape,
|
643 |
+
cond,
|
644 |
+
verbose=False,
|
645 |
+
eta=eta,
|
646 |
+
unconditional_guidance_scale=scale,
|
647 |
+
unconditional_conditioning=un_cond)
|
648 |
+
|
649 |
+
if config.save_memory:
|
650 |
+
self.model.low_vram_shift(is_diffusing=False)
|
651 |
+
|
652 |
+
x_samples = self.model.decode_first_stage(samples)
|
653 |
+
x_samples = (
|
654 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
655 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
656 |
+
|
657 |
+
results = [x_samples[i] for i in range(num_samples)]
|
658 |
+
return [detected_map] + results
|
659 |
+
|
660 |
+
@torch.inference_mode()
|
661 |
+
def process_normal(self, input_image, prompt, a_prompt, n_prompt,
|
662 |
+
num_samples, image_resolution, detect_resolution,
|
663 |
+
ddim_steps, scale, seed, eta, bg_threshold):
|
664 |
+
self.load_weight('normal')
|
665 |
+
|
666 |
+
input_image = HWC3(input_image)
|
667 |
+
_, detected_map = apply_midas(resize_image(input_image,
|
668 |
+
detect_resolution),
|
669 |
+
bg_th=bg_threshold)
|
670 |
+
detected_map = HWC3(detected_map)
|
671 |
+
img = resize_image(input_image, image_resolution)
|
672 |
+
H, W, C = img.shape
|
673 |
+
|
674 |
+
detected_map = cv2.resize(detected_map, (W, H),
|
675 |
+
interpolation=cv2.INTER_LINEAR)
|
676 |
+
|
677 |
+
control = torch.from_numpy(
|
678 |
+
detected_map[:, :, ::-1].copy()).float().cuda() / 255.0
|
679 |
+
control = torch.stack([control for _ in range(num_samples)], dim=0)
|
680 |
+
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
|
681 |
+
|
682 |
+
if seed == -1:
|
683 |
+
seed = random.randint(0, 65535)
|
684 |
+
seed_everything(seed)
|
685 |
+
|
686 |
+
if config.save_memory:
|
687 |
+
self.model.low_vram_shift(is_diffusing=False)
|
688 |
+
|
689 |
+
cond = {
|
690 |
+
'c_concat': [control],
|
691 |
+
'c_crossattn': [
|
692 |
+
self.model.get_learned_conditioning(
|
693 |
+
[prompt + ', ' + a_prompt] * num_samples)
|
694 |
+
]
|
695 |
+
}
|
696 |
+
un_cond = {
|
697 |
+
'c_concat': [control],
|
698 |
+
'c_crossattn':
|
699 |
+
[self.model.get_learned_conditioning([n_prompt] * num_samples)]
|
700 |
+
}
|
701 |
+
shape = (4, H // 8, W // 8)
|
702 |
+
|
703 |
+
if config.save_memory:
|
704 |
+
self.model.low_vram_shift(is_diffusing=True)
|
705 |
+
|
706 |
+
samples, intermediates = self.ddim_sampler.sample(
|
707 |
+
ddim_steps,
|
708 |
+
num_samples,
|
709 |
+
shape,
|
710 |
+
cond,
|
711 |
+
verbose=False,
|
712 |
+
eta=eta,
|
713 |
+
unconditional_guidance_scale=scale,
|
714 |
+
unconditional_conditioning=un_cond)
|
715 |
+
|
716 |
+
if config.save_memory:
|
717 |
+
self.model.low_vram_shift(is_diffusing=False)
|
718 |
+
|
719 |
+
x_samples = self.model.decode_first_stage(samples)
|
720 |
+
x_samples = (
|
721 |
+
einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
|
722 |
+
127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
|
723 |
+
|
724 |
+
results = [x_samples[i] for i in range(num_samples)]
|
725 |
+
return [detected_map] + results
|
patch
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
diff --git a/annotator/hed/__init__.py b/annotator/hed/__init__.py
|
2 |
+
index 42d8dc6..1587035 100644
|
3 |
+
--- a/annotator/hed/__init__.py
|
4 |
+
+++ b/annotator/hed/__init__.py
|
5 |
+
@@ -1,8 +1,12 @@
|
6 |
+
+import pathlib
|
7 |
+
+
|
8 |
+
import numpy as np
|
9 |
+
import cv2
|
10 |
+
import torch
|
11 |
+
from einops import rearrange
|
12 |
+
|
13 |
+
+root_dir = pathlib.Path(__file__).parents[2]
|
14 |
+
+
|
15 |
+
|
16 |
+
class Network(torch.nn.Module):
|
17 |
+
def __init__(self):
|
18 |
+
@@ -64,7 +68,7 @@ class Network(torch.nn.Module):
|
19 |
+
torch.nn.Sigmoid()
|
20 |
+
)
|
21 |
+
|
22 |
+
- self.load_state_dict({strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.load('./annotator/ckpts/network-bsds500.pth').items()})
|
23 |
+
+ self.load_state_dict({strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.load(f'{root_dir}/annotator/ckpts/network-bsds500.pth').items()})
|
24 |
+
# end
|
25 |
+
|
26 |
+
def forward(self, tenInput):
|
27 |
+
diff --git a/annotator/midas/api.py b/annotator/midas/api.py
|
28 |
+
index 9fa305e..d8594ea 100644
|
29 |
+
--- a/annotator/midas/api.py
|
30 |
+
+++ b/annotator/midas/api.py
|
31 |
+
@@ -1,5 +1,7 @@
|
32 |
+
# based on https://github.com/isl-org/MiDaS
|
33 |
+
|
34 |
+
+import pathlib
|
35 |
+
+
|
36 |
+
import cv2
|
37 |
+
import torch
|
38 |
+
import torch.nn as nn
|
39 |
+
@@ -10,10 +12,11 @@ from .midas.midas_net import MidasNet
|
40 |
+
from .midas.midas_net_custom import MidasNet_small
|
41 |
+
from .midas.transforms import Resize, NormalizeImage, PrepareForNet
|
42 |
+
|
43 |
+
+root_dir = pathlib.Path(__file__).parents[2]
|
44 |
+
|
45 |
+
ISL_PATHS = {
|
46 |
+
- "dpt_large": "annotator/ckpts/dpt_large-midas-2f21e586.pt",
|
47 |
+
- "dpt_hybrid": "annotator/ckpts/dpt_hybrid-midas-501f0c75.pt",
|
48 |
+
+ "dpt_large": f"{root_dir}/annotator/ckpts/dpt_large-midas-2f21e586.pt",
|
49 |
+
+ "dpt_hybrid": f"{root_dir}/annotator/ckpts/dpt_hybrid-midas-501f0c75.pt",
|
50 |
+
"midas_v21": "",
|
51 |
+
"midas_v21_small": "",
|
52 |
+
}
|
53 |
+
diff --git a/annotator/mlsd/__init__.py b/annotator/mlsd/__init__.py
|
54 |
+
index 75db717..f310fe6 100644
|
55 |
+
--- a/annotator/mlsd/__init__.py
|
56 |
+
+++ b/annotator/mlsd/__init__.py
|
57 |
+
@@ -1,3 +1,5 @@
|
58 |
+
+import pathlib
|
59 |
+
+
|
60 |
+
import cv2
|
61 |
+
import numpy as np
|
62 |
+
import torch
|
63 |
+
@@ -8,8 +10,9 @@ from .models.mbv2_mlsd_tiny import MobileV2_MLSD_Tiny
|
64 |
+
from .models.mbv2_mlsd_large import MobileV2_MLSD_Large
|
65 |
+
from .utils import pred_lines
|
66 |
+
|
67 |
+
+root_dir = pathlib.Path(__file__).parents[2]
|
68 |
+
|
69 |
+
-model_path = './annotator/ckpts/mlsd_large_512_fp32.pth'
|
70 |
+
+model_path = f'{root_dir}/annotator/ckpts/mlsd_large_512_fp32.pth'
|
71 |
+
model = MobileV2_MLSD_Large()
|
72 |
+
model.load_state_dict(torch.load(model_path), strict=True)
|
73 |
+
model = model.cuda().eval()
|
74 |
+
diff --git a/annotator/openpose/__init__.py b/annotator/openpose/__init__.py
|
75 |
+
index 47d50a5..2369eed 100644
|
76 |
+
--- a/annotator/openpose/__init__.py
|
77 |
+
+++ b/annotator/openpose/__init__.py
|
78 |
+
@@ -1,4 +1,5 @@
|
79 |
+
import os
|
80 |
+
+import pathlib
|
81 |
+
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
|
82 |
+
|
83 |
+
import torch
|
84 |
+
@@ -7,8 +8,10 @@ from . import util
|
85 |
+
from .body import Body
|
86 |
+
from .hand import Hand
|
87 |
+
|
88 |
+
-body_estimation = Body('./annotator/ckpts/body_pose_model.pth')
|
89 |
+
-hand_estimation = Hand('./annotator/ckpts/hand_pose_model.pth')
|
90 |
+
+root_dir = pathlib.Path(__file__).parents[2]
|
91 |
+
+
|
92 |
+
+body_estimation = Body(f'{root_dir}/annotator/ckpts/body_pose_model.pth')
|
93 |
+
+hand_estimation = Hand(f'{root_dir}/annotator/ckpts/hand_pose_model.pth')
|
94 |
+
|
95 |
+
|
96 |
+
def apply_openpose(oriImg, hand=False):
|
97 |
+
diff --git a/annotator/uniformer/__init__.py b/annotator/uniformer/__init__.py
|
98 |
+
index 500e53c..4061dbe 100644
|
99 |
+
--- a/annotator/uniformer/__init__.py
|
100 |
+
+++ b/annotator/uniformer/__init__.py
|
101 |
+
@@ -1,9 +1,12 @@
|
102 |
+
+import pathlib
|
103 |
+
+
|
104 |
+
from annotator.uniformer.mmseg.apis import init_segmentor, inference_segmentor, show_result_pyplot
|
105 |
+
from annotator.uniformer.mmseg.core.evaluation import get_palette
|
106 |
+
|
107 |
+
+root_dir = pathlib.Path(__file__).parents[2]
|
108 |
+
|
109 |
+
-checkpoint_file = "annotator/ckpts/upernet_global_small.pth"
|
110 |
+
-config_file = 'annotator/uniformer/exp/upernet_global_small/config.py'
|
111 |
+
+checkpoint_file = f"{root_dir}/annotator/ckpts/upernet_global_small.pth"
|
112 |
+
+config_file = f'{root_dir}/annotator/uniformer/exp/upernet_global_small/config.py'
|
113 |
+
model = init_segmentor(config_file, checkpoint_file).cuda()
|
114 |
+
|
115 |
+
|
requirements.txt
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
addict==2.4.0
|
2 |
+
albumentations==1.3.0
|
3 |
+
einops==0.6.0
|
4 |
+
gradio==3.18.0
|
5 |
+
imageio==2.25.0
|
6 |
+
imageio-ffmpeg==0.4.8
|
7 |
+
kornia==0.6.9
|
8 |
+
omegaconf==2.3.0
|
9 |
+
open-clip-torch==2.13.0
|
10 |
+
opencv-contrib-python==4.7.0.68
|
11 |
+
opencv-python-headless==4.7.0.68
|
12 |
+
prettytable==3.6.0
|
13 |
+
pytorch-lightning==1.9.0
|
14 |
+
timm==0.6.12
|
15 |
+
torch==1.13.1
|
16 |
+
torchvision==0.14.1
|
17 |
+
transformers==4.26.1
|
18 |
+
yapf==0.32.0
|
style.css
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
h1 {
|
2 |
+
text-align: center;
|
3 |
+
}
|