Duplicate from hysts/ControlNet

Co-authored-by: hysts <hysts@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,162 @@
+models/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "ControlNet"]
+	path = ControlNet
+	url = https://github.com/lllyasviel/ControlNet

.pre-commit-config.yaml

@@ -0,0 +1,47 @@
+exclude: patch
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.2.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: double-quote-string-fixer
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ['--fix=lf']
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.4
+  hooks:
+  - id: docformatter
+    args: ['--in-place']
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.991
+  hooks:
+    - id: mypy
+      args: ['--ignore-missing-imports']
+      additional_dependencies: ['types-python-slugify']
+- repo: https://github.com/google/yapf
+  rev: v0.32.0
+  hooks:
+  - id: yapf
+    args: ['--parallel', '--in-place']
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.6.0
+  hooks:
+    - id: nbstripout
+      args: ['--extra-keys', 'metadata.interpreter metadata.kernelspec cell.metadata.pycharm']
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.6.4
+  hooks:
+    - id: nbqa-isort
+    - id: nbqa-yapf

.style.yapf

@@ -0,0 +1,5 @@
+[style]
+based_on_style = pep8
+blank_line_before_nested_class_or_def = false
+spaces_before_comment = 2
+split_before_logical_operator = true

ControlNet

@@ -0,0 +1 @@
+Subproject commit f4748e3630d8141d7765e2bd9b1e348f47847707

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 hysts
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

LICENSE.ControlNet

@@ -0,0 +1,201 @@
+                                 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.

README.md

@@ -0,0 +1,15 @@
+---
+title: ControlNet
+emoji: 🌖
+colorFrom: pink
+colorTo: blue
+sdk: gradio
+sdk_version: 3.23.0
+python_version: 3.10.9
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: hysts/ControlNet
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,158 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import os
+import pathlib
+import shlex
+import subprocess
+
+import gradio as gr
+import torch
+
+if os.getenv('SYSTEM') == 'spaces':
+    with open('patch') as f:
+        subprocess.run(shlex.split('patch -p1'), stdin=f, cwd='ControlNet')
+
+base_url = 'https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/'
+names = [
+    'body_pose_model.pth',
+    'dpt_hybrid-midas-501f0c75.pt',
+    'hand_pose_model.pth',
+    'mlsd_large_512_fp32.pth',
+    'mlsd_tiny_512_fp32.pth',
+    'network-bsds500.pth',
+    'upernet_global_small.pth',
+]
+for name in names:
+    command = f'wget https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/{name} -O {name}'
+    out_path = pathlib.Path(f'ControlNet/annotator/ckpts/{name}')
+    if out_path.exists():
+        continue
+    subprocess.run(shlex.split(command), cwd='ControlNet/annotator/ckpts/')
+
+from app_canny import create_demo as create_demo_canny
+from app_depth import create_demo as create_demo_depth
+from app_fake_scribble import create_demo as create_demo_fake_scribble
+from app_hed import create_demo as create_demo_hed
+from app_hough import create_demo as create_demo_hough
+from app_normal import create_demo as create_demo_normal
+from app_pose import create_demo as create_demo_pose
+from app_scribble import create_demo as create_demo_scribble
+from app_scribble_interactive import \
+    create_demo as create_demo_scribble_interactive
+from app_seg import create_demo as create_demo_seg
+from model import Model, download_all_controlnet_weights
+
+DESCRIPTION = '''# [ControlNet v1.0](https://github.com/lllyasviel/ControlNet)
+
+<p class="note">New ControlNet v1.1 is available <a href="https://huggingface.co/spaces/hysts/ControlNet-v1-1">here</a>.</p>
+'''
+
+SPACE_ID = os.getenv('SPACE_ID')
+ALLOW_CHANGING_BASE_MODEL = SPACE_ID != 'hysts/ControlNet'
+
+if SPACE_ID is not None:
+    DESCRIPTION += f'\n<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p>'
+
+if torch.cuda.is_available():
+    DESCRIPTION += '\n<p>Running on GPU 🔥</p>'
+    if os.getenv('SYSTEM') == 'spaces':
+        download_all_controlnet_weights()
+else:
+    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.'
+
+MAX_IMAGES = int(os.getenv('MAX_IMAGES', '3'))
+DEFAULT_NUM_IMAGES = min(MAX_IMAGES, int(os.getenv('DEFAULT_NUM_IMAGES', '1')))
+
+DEFAULT_MODEL_ID = os.getenv('DEFAULT_MODEL_ID',
+                             'runwayml/stable-diffusion-v1-5')
+model = Model(base_model_id=DEFAULT_MODEL_ID, task_name='canny')
+
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(DESCRIPTION)
+    with gr.Tabs():
+        with gr.TabItem('Canny'):
+            create_demo_canny(model.process_canny,
+                              max_images=MAX_IMAGES,
+                              default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Hough'):
+            create_demo_hough(model.process_hough,
+                              max_images=MAX_IMAGES,
+                              default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('HED'):
+            create_demo_hed(model.process_hed,
+                            max_images=MAX_IMAGES,
+                            default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Scribble'):
+            create_demo_scribble(model.process_scribble,
+                                 max_images=MAX_IMAGES,
+                                 default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Scribble Interactive'):
+            create_demo_scribble_interactive(
+                model.process_scribble_interactive,
+                max_images=MAX_IMAGES,
+                default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Fake Scribble'):
+            create_demo_fake_scribble(model.process_fake_scribble,
+                                      max_images=MAX_IMAGES,
+                                      default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Pose'):
+            create_demo_pose(model.process_pose,
+                             max_images=MAX_IMAGES,
+                             default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Segmentation'):
+            create_demo_seg(model.process_seg,
+                            max_images=MAX_IMAGES,
+                            default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Depth'):
+            create_demo_depth(model.process_depth,
+                              max_images=MAX_IMAGES,
+                              default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Normal map'):
+            create_demo_normal(model.process_normal,
+                               max_images=MAX_IMAGES,
+                               default_num_images=DEFAULT_NUM_IMAGES)
+
+    with gr.Accordion(label='Base model', open=False):
+        with gr.Row():
+            with gr.Column():
+                current_base_model = gr.Text(label='Current base model')
+            with gr.Column(scale=0.3):
+                check_base_model_button = gr.Button('Check current base model')
+        with gr.Row():
+            with gr.Column():
+                new_base_model_id = gr.Text(
+                    label='New base model',
+                    max_lines=1,
+                    placeholder='runwayml/stable-diffusion-v1-5',
+                    info=
+                    'The base model must be compatible with Stable Diffusion v1.5.',
+                    interactive=ALLOW_CHANGING_BASE_MODEL)
+            with gr.Column(scale=0.3):
+                change_base_model_button = gr.Button(
+                    'Change base model', interactive=ALLOW_CHANGING_BASE_MODEL)
+        if not ALLOW_CHANGING_BASE_MODEL:
+            gr.Markdown(
+                '''The base model is not allowed to be changed in this Space so as not to slow down the demo, but it can be changed if you duplicate the Space. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a>'''
+            )
+
+    gr.Markdown('''### Related Spaces
+
+- [Space using Anything-v4.0 as base model](https://huggingface.co/spaces/hysts/ControlNet-with-Anything-v4)
+- https://huggingface.co/spaces/jonigata/PoseMaker2
+- https://huggingface.co/spaces/diffusers/controlnet-openpose
+- https://huggingface.co/spaces/diffusers/controlnet-canny
+''')
+
+    check_base_model_button.click(fn=lambda: model.base_model_id,
+                                  outputs=current_base_model,
+                                  queue=False)
+    new_base_model_id.submit(fn=model.set_base_model,
+                             inputs=new_base_model_id,
+                             outputs=current_base_model)
+    change_base_model_button.click(fn=model.set_base_model,
+                                   inputs=new_base_model_id,
+                                   outputs=current_base_model)
+
+demo.queue(api_open=False, max_size=10).launch()

app_canny.py

@@ -0,0 +1,91 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_canny2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Canny Edge Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    canny_low_threshold = gr.Slider(
+                        label='Canny low threshold',
+                        minimum=1,
+                        maximum=255,
+                        value=100,
+                        step=1)
+                    canny_high_threshold = gr.Slider(
+                        label='Canny high threshold',
+                        minimum=1,
+                        maximum=255,
+                        value=200,
+                        step=1)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            canny_low_threshold,
+            canny_high_threshold,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='canny')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_canny)
+    demo.queue().launch()

app_depth.py

@@ -0,0 +1,86 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_depth2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Depth Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    is_depth_image = gr.Checkbox(label='Is depth image',
+                                                 value=False)
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='Depth Resolution',
+                                                  minimum=128,
+                                                  maximum=512,
+                                                  value=384,
+                                                  step=1)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            detect_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            is_depth_image,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='depth')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_depth)
+    demo.queue().launch()

app_fake_scribble.py

@@ -0,0 +1,83 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_fake_scribble2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Fake Scribble Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='HED Resolution',
+                                                  minimum=128,
+                                                  maximum=512,
+                                                  value=512,
+                                                  step=1)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            detect_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='fake_scribble')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_fake_scribble)
+    demo.queue().launch()

app_hed.py

@@ -0,0 +1,83 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_hed2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with HED Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='HED Resolution',
+                                                  minimum=128,
+                                                  maximum=512,
+                                                  value=512,
+                                                  step=1)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            detect_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='hed')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_hed)
+    demo.queue().launch()

app_hough.py

@@ -0,0 +1,97 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_hough2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Hough Line Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='Hough Resolution',
+                                                  minimum=128,
+                                                  maximum=512,
+                                                  value=512,
+                                                  step=1)
+                    mlsd_value_threshold = gr.Slider(
+                        label='Hough value threshold (MLSD)',
+                        minimum=0.01,
+                        maximum=2.0,
+                        value=0.1,
+                        step=0.01)
+                    mlsd_distance_threshold = gr.Slider(
+                        label='Hough distance threshold (MLSD)',
+                        minimum=0.01,
+                        maximum=20.0,
+                        value=0.1,
+                        step=0.01)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            detect_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            mlsd_value_threshold,
+            mlsd_distance_threshold,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='hough')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_hough)
+    demo.queue().launch()

app_normal.py

@@ -0,0 +1,93 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_normal2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Normal Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    is_normal_image = gr.Checkbox(label='Is normal image',
+                                                  value=False)
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='Normal Resolution',
+                                                  minimum=128,
+                                                  maximum=512,
+                                                  value=384,
+                                                  step=1)
+                    bg_threshold = gr.Slider(
+                        label='Normal background threshold',
+                        minimum=0.0,
+                        maximum=1.0,
+                        value=0.4,
+                        step=0.01)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            detect_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            bg_threshold,
+            is_normal_image,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='normal')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_normal)
+    demo.queue().launch()

app_pose.py

@@ -0,0 +1,89 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_pose2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Human Pose')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    is_pose_image = gr.Checkbox(label='Is pose image',
+                                                value=False)
+                    gr.Markdown(
+                        'You can use [PoseMaker2](https://huggingface.co/spaces/jonigata/PoseMaker2) to create pose images.'
+                    )
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='OpenPose Resolution',
+                                                  minimum=128,
+                                                  maximum=512,
+                                                  value=512,
+                                                  step=1)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            detect_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            is_pose_image,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='pose')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_pose)
+    demo.queue().launch()

app_scribble.py

@@ -0,0 +1,77 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_scribble2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Scribble Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='scribble')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_scribble)
+    demo.queue().launch()

app_scribble_interactive.py

@@ -0,0 +1,103 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_scribble2image_interactive.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+import numpy as np
+
+
+def create_canvas(w, h):
+    return np.zeros(shape=(h, w, 3), dtype=np.uint8) + 255
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown(
+                '## Control Stable Diffusion with Interactive Scribbles')
+        with gr.Row():
+            with gr.Column():
+                canvas_width = gr.Slider(label='Canvas Width',
+                                         minimum=256,
+                                         maximum=512,
+                                         value=512,
+                                         step=1)
+                canvas_height = gr.Slider(label='Canvas Height',
+                                          minimum=256,
+                                          maximum=512,
+                                          value=512,
+                                          step=1)
+                create_button = gr.Button(label='Start',
+                                          value='Open drawing canvas!')
+                input_image = gr.Image(source='upload',
+                                       type='numpy',
+                                       tool='sketch')
+                gr.Markdown(
+                    value=
+                    '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.) '
+                    'Just click on the small pencil icon in the upper right corner of the above block.'
+                )
+                create_button.click(fn=create_canvas,
+                                    inputs=[canvas_width, canvas_height],
+                                    outputs=input_image,
+                                    queue=False)
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process, inputs=inputs, outputs=result)
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_scribble_interactive)
+    demo.queue().launch()

app_seg.py

@@ -0,0 +1,87 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_seg2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Segmentation Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    is_segmentation_map = gr.Checkbox(
+                        label='Is segmentation map', value=False)
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=default_num_images,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=512,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(
+                        label='Segmentation Resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=512,
+                        step=1)
+                    num_steps = gr.Slider(label='Steps',
+                                          minimum=1,
+                                          maximum=100,
+                                          value=20,
+                                          step=1)
+                    guidance_scale = gr.Slider(label='Guidance Scale',
+                                               minimum=0.1,
+                                               maximum=30.0,
+                                               value=9.0,
+                                               step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result = gr.Gallery(label='Output',
+                                    show_label=False,
+                                    elem_id='gallery').style(grid=2,
+                                                             height='auto')
+        inputs = [
+            input_image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            detect_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            is_segmentation_map,
+        ]
+        prompt.submit(fn=process, inputs=inputs, outputs=result)
+        run_button.click(fn=process,
+                         inputs=inputs,
+                         outputs=result,
+                         api_name='seg')
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model()
+    demo = create_demo(model.process_seg)
+    demo.queue().launch()

model.py

@@ -0,0 +1,649 @@
+# This file is adapted from gradio_*.py in https://github.com/lllyasviel/ControlNet/tree/f4748e3630d8141d7765e2bd9b1e348f47847707
+# The original license file is LICENSE.ControlNet in this repo.
+from __future__ import annotations
+
+import gc
+import pathlib
+import sys
+
+import cv2
+import numpy as np
+import PIL.Image
+import torch
+from diffusers import (ControlNetModel, DiffusionPipeline,
+                       StableDiffusionControlNetPipeline,
+                       UniPCMultistepScheduler)
+
+repo_dir = pathlib.Path(__file__).parent
+submodule_dir = repo_dir / 'ControlNet'
+sys.path.append(submodule_dir.as_posix())
+
+try:
+    from annotator.canny import apply_canny
+    from annotator.hed import apply_hed, nms
+    from annotator.midas import apply_midas
+    from annotator.mlsd import apply_mlsd
+    from annotator.openpose import apply_openpose
+    from annotator.uniformer import apply_uniformer
+    from annotator.util import HWC3, resize_image
+except Exception:
+    pass
+
+CONTROLNET_MODEL_IDS = {
+    'canny': 'lllyasviel/sd-controlnet-canny',
+    'hough': 'lllyasviel/sd-controlnet-mlsd',
+    'hed': 'lllyasviel/sd-controlnet-hed',
+    'scribble': 'lllyasviel/sd-controlnet-scribble',
+    'pose': 'lllyasviel/sd-controlnet-openpose',
+    'seg': 'lllyasviel/sd-controlnet-seg',
+    'depth': 'lllyasviel/sd-controlnet-depth',
+    'normal': 'lllyasviel/sd-controlnet-normal',
+}
+
+
+def download_all_controlnet_weights() -> None:
+    for model_id in CONTROLNET_MODEL_IDS.values():
+        ControlNetModel.from_pretrained(model_id)
+
+
+class Model:
+    def __init__(self,
+                 base_model_id: str = 'runwayml/stable-diffusion-v1-5',
+                 task_name: str = 'canny'):
+        self.device = torch.device(
+            'cuda:0' if torch.cuda.is_available() else 'cpu')
+        self.base_model_id = ''
+        self.task_name = ''
+        self.pipe = self.load_pipe(base_model_id, task_name)
+
+    def load_pipe(self, base_model_id: str, task_name) -> DiffusionPipeline:
+        if self.device.type == 'cpu':
+            return None
+        if base_model_id == self.base_model_id and task_name == self.task_name and hasattr(
+                self, 'pipe'):
+            return self.pipe
+        model_id = CONTROLNET_MODEL_IDS[task_name]
+        controlnet = ControlNetModel.from_pretrained(model_id,
+                                                     torch_dtype=torch.float16)
+        pipe = StableDiffusionControlNetPipeline.from_pretrained(
+            base_model_id,
+            safety_checker=None,
+            controlnet=controlnet,
+            torch_dtype=torch.float16)
+        pipe.scheduler = UniPCMultistepScheduler.from_config(
+            pipe.scheduler.config)
+        pipe.enable_xformers_memory_efficient_attention()
+        pipe.to(self.device)
+        torch.cuda.empty_cache()
+        gc.collect()
+        self.base_model_id = base_model_id
+        self.task_name = task_name
+        return pipe
+
+    def set_base_model(self, base_model_id: str) -> str:
+        if not base_model_id or base_model_id == self.base_model_id:
+            return self.base_model_id
+        del self.pipe
+        torch.cuda.empty_cache()
+        gc.collect()
+        try:
+            self.pipe = self.load_pipe(base_model_id, self.task_name)
+        except Exception:
+            self.pipe = self.load_pipe(self.base_model_id, self.task_name)
+        return self.base_model_id
+
+    def load_controlnet_weight(self, task_name: str) -> None:
+        if task_name == self.task_name:
+            return
+        if 'controlnet' in self.pipe.__dict__:
+            del self.pipe.controlnet
+        torch.cuda.empty_cache()
+        gc.collect()
+        model_id = CONTROLNET_MODEL_IDS[task_name]
+        controlnet = ControlNetModel.from_pretrained(model_id,
+                                                     torch_dtype=torch.float16)
+        controlnet.to(self.device)
+        torch.cuda.empty_cache()
+        gc.collect()
+        self.pipe.controlnet = controlnet
+        self.task_name = task_name
+
+    def get_prompt(self, prompt: str, additional_prompt: str) -> str:
+        if not prompt:
+            prompt = additional_prompt
+        else:
+            prompt = f'{prompt}, {additional_prompt}'
+        return prompt
+
+    @torch.autocast('cuda')
+    def run_pipe(
+        self,
+        prompt: str,
+        negative_prompt: str,
+        control_image: PIL.Image.Image,
+        num_images: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+    ) -> list[PIL.Image.Image]:
+        if seed == -1:
+            seed = np.random.randint(0, np.iinfo(np.int64).max)
+        generator = torch.Generator().manual_seed(seed)
+        return self.pipe(prompt=prompt,
+                         negative_prompt=negative_prompt,
+                         guidance_scale=guidance_scale,
+                         num_images_per_prompt=num_images,
+                         num_inference_steps=num_steps,
+                         generator=generator,
+                         image=control_image).images
+
+    @staticmethod
+    def preprocess_canny(
+        input_image: np.ndarray,
+        image_resolution: int,
+        low_threshold: int,
+        high_threshold: int,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        image = resize_image(HWC3(input_image), image_resolution)
+        control_image = apply_canny(image, low_threshold, high_threshold)
+        control_image = HWC3(control_image)
+        vis_control_image = 255 - control_image
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            vis_control_image)
+
+    @torch.inference_mode()
+    def process_canny(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        low_threshold: int,
+        high_threshold: int,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_canny(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            low_threshold=low_threshold,
+            high_threshold=high_threshold,
+        )
+        self.load_controlnet_weight('canny')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_hough(
+        input_image: np.ndarray,
+        image_resolution: int,
+        detect_resolution: int,
+        value_threshold: float,
+        distance_threshold: float,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        input_image = HWC3(input_image)
+        control_image = apply_mlsd(
+            resize_image(input_image, detect_resolution), value_threshold,
+            distance_threshold)
+        control_image = HWC3(control_image)
+        image = resize_image(input_image, image_resolution)
+        H, W = image.shape[:2]
+        control_image = cv2.resize(control_image, (W, H),
+                                   interpolation=cv2.INTER_NEAREST)
+
+        vis_control_image = 255 - cv2.dilate(
+            control_image, np.ones(shape=(3, 3), dtype=np.uint8), iterations=1)
+
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            vis_control_image)
+
+    @torch.inference_mode()
+    def process_hough(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        detect_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        value_threshold: float,
+        distance_threshold: float,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_hough(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            detect_resolution=detect_resolution,
+            value_threshold=value_threshold,
+            distance_threshold=distance_threshold,
+        )
+        self.load_controlnet_weight('hough')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_hed(
+        input_image: np.ndarray,
+        image_resolution: int,
+        detect_resolution: int,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        input_image = HWC3(input_image)
+        control_image = apply_hed(resize_image(input_image, detect_resolution))
+        control_image = HWC3(control_image)
+        image = resize_image(input_image, image_resolution)
+        H, W = image.shape[:2]
+        control_image = cv2.resize(control_image, (W, H),
+                                   interpolation=cv2.INTER_LINEAR)
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            control_image)
+
+    @torch.inference_mode()
+    def process_hed(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        detect_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_hed(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            detect_resolution=detect_resolution,
+        )
+        self.load_controlnet_weight('hed')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_scribble(
+        input_image: np.ndarray,
+        image_resolution: int,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        image = resize_image(HWC3(input_image), image_resolution)
+        control_image = np.zeros_like(image, dtype=np.uint8)
+        control_image[np.min(image, axis=2) < 127] = 255
+        vis_control_image = 255 - control_image
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            vis_control_image)
+
+    @torch.inference_mode()
+    def process_scribble(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_scribble(
+            input_image=input_image,
+            image_resolution=image_resolution,
+        )
+        self.load_controlnet_weight('scribble')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_scribble_interactive(
+        input_image: np.ndarray,
+        image_resolution: int,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        image = resize_image(HWC3(input_image['mask'][:, :, 0]),
+                             image_resolution)
+        control_image = np.zeros_like(image, dtype=np.uint8)
+        control_image[np.min(image, axis=2) > 127] = 255
+        vis_control_image = 255 - control_image
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            vis_control_image)
+
+    @torch.inference_mode()
+    def process_scribble_interactive(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_scribble_interactive(
+            input_image=input_image,
+            image_resolution=image_resolution,
+        )
+        self.load_controlnet_weight('scribble')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_fake_scribble(
+        input_image: np.ndarray,
+        image_resolution: int,
+        detect_resolution: int,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        input_image = HWC3(input_image)
+        control_image = apply_hed(resize_image(input_image, detect_resolution))
+        control_image = HWC3(control_image)
+        image = resize_image(input_image, image_resolution)
+        H, W = image.shape[:2]
+
+        control_image = cv2.resize(control_image, (W, H),
+                                   interpolation=cv2.INTER_LINEAR)
+        control_image = nms(control_image, 127, 3.0)
+        control_image = cv2.GaussianBlur(control_image, (0, 0), 3.0)
+        control_image[control_image > 4] = 255
+        control_image[control_image < 255] = 0
+
+        vis_control_image = 255 - control_image
+
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            vis_control_image)
+
+    @torch.inference_mode()
+    def process_fake_scribble(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        detect_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_fake_scribble(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            detect_resolution=detect_resolution,
+        )
+        self.load_controlnet_weight('scribble')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_pose(
+        input_image: np.ndarray,
+        image_resolution: int,
+        detect_resolution: int,
+        is_pose_image: bool,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        input_image = HWC3(input_image)
+        if not is_pose_image:
+            control_image, _ = apply_openpose(
+                resize_image(input_image, detect_resolution))
+            control_image = HWC3(control_image)
+            image = resize_image(input_image, image_resolution)
+            H, W = image.shape[:2]
+            control_image = cv2.resize(control_image, (W, H),
+                                       interpolation=cv2.INTER_NEAREST)
+        else:
+            control_image = resize_image(input_image, image_resolution)
+
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            control_image)
+
+    @torch.inference_mode()
+    def process_pose(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        detect_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        is_pose_image: bool,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_pose(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            detect_resolution=detect_resolution,
+            is_pose_image=is_pose_image,
+        )
+        self.load_controlnet_weight('pose')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_seg(
+        input_image: np.ndarray,
+        image_resolution: int,
+        detect_resolution: int,
+        is_segmentation_map: bool,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        input_image = HWC3(input_image)
+        if not is_segmentation_map:
+            control_image = apply_uniformer(
+                resize_image(input_image, detect_resolution))
+            image = resize_image(input_image, image_resolution)
+            H, W = image.shape[:2]
+            control_image = cv2.resize(control_image, (W, H),
+                                       interpolation=cv2.INTER_NEAREST)
+        else:
+            control_image = resize_image(input_image, image_resolution)
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            control_image)
+
+    @torch.inference_mode()
+    def process_seg(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        detect_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        is_segmentation_map: bool,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_seg(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            detect_resolution=detect_resolution,
+            is_segmentation_map=is_segmentation_map,
+        )
+        self.load_controlnet_weight('seg')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_depth(
+        input_image: np.ndarray,
+        image_resolution: int,
+        detect_resolution: int,
+        is_depth_image: bool,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        input_image = HWC3(input_image)
+        if not is_depth_image:
+            control_image, _ = apply_midas(
+                resize_image(input_image, detect_resolution))
+            control_image = HWC3(control_image)
+            image = resize_image(input_image, image_resolution)
+            H, W = image.shape[:2]
+            control_image = cv2.resize(control_image, (W, H),
+                                       interpolation=cv2.INTER_LINEAR)
+        else:
+            control_image = resize_image(input_image, image_resolution)
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            control_image)
+
+    @torch.inference_mode()
+    def process_depth(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        detect_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        is_depth_image: bool,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_depth(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            detect_resolution=detect_resolution,
+            is_depth_image=is_depth_image,
+        )
+        self.load_controlnet_weight('depth')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results
+
+    @staticmethod
+    def preprocess_normal(
+        input_image: np.ndarray,
+        image_resolution: int,
+        detect_resolution: int,
+        bg_threshold: float,
+        is_normal_image: bool,
+    ) -> tuple[PIL.Image.Image, PIL.Image.Image]:
+        input_image = HWC3(input_image)
+        if not is_normal_image:
+            _, control_image = apply_midas(resize_image(
+                input_image, detect_resolution),
+                                           bg_th=bg_threshold)
+            control_image = HWC3(control_image)
+            image = resize_image(input_image, image_resolution)
+            H, W = image.shape[:2]
+            control_image = cv2.resize(control_image, (W, H),
+                                       interpolation=cv2.INTER_LINEAR)
+        else:
+            control_image = resize_image(input_image, image_resolution)
+        return PIL.Image.fromarray(control_image), PIL.Image.fromarray(
+            control_image)
+
+    @torch.inference_mode()
+    def process_normal(
+        self,
+        input_image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        detect_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        bg_threshold: float,
+        is_normal_image: bool,
+    ) -> list[PIL.Image.Image]:
+        control_image, vis_control_image = self.preprocess_normal(
+            input_image=input_image,
+            image_resolution=image_resolution,
+            detect_resolution=detect_resolution,
+            bg_threshold=bg_threshold,
+            is_normal_image=is_normal_image,
+        )
+        self.load_controlnet_weight('normal')
+        results = self.run_pipe(
+            prompt=self.get_prompt(prompt, additional_prompt),
+            negative_prompt=negative_prompt,
+            control_image=control_image,
+            num_images=num_images,
+            num_steps=num_steps,
+            guidance_scale=guidance_scale,
+            seed=seed,
+        )
+        return [vis_control_image] + results

notebooks/notebook.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "8CnkIPtjn8Dc"
+   },
+   "outputs": [],
+   "source": [
+    "!git clone --recursive https://huggingface.co/spaces/hysts/ControlNet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "IZlaYNTWoFPK"
+   },
+   "outputs": [],
+   "source": [
+    "%cd ControlNet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "0zhLFnZUoWdp"
+   },
+   "outputs": [],
+   "source": [
+    "!cd ControlNet && git apply ../patch && cd .."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "P_fzYrLvoIcI"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install -q -r requirements.txt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "GOfGng5Woktd"
+   },
+   "outputs": [],
+   "source": [
+    "import app"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "7Cued230ol7T"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

patch

@@ -0,0 +1,128 @@
+diff --git a/annotator/hed/__init__.py b/annotator/hed/__init__.py
+index 42d8dc6..1587035 100644
+--- a/annotator/hed/__init__.py
++++ b/annotator/hed/__init__.py
+@@ -1,8 +1,12 @@
++import pathlib
++
+ import numpy as np
+ import cv2
+ import torch
+ from einops import rearrange
+ 
++root_dir = pathlib.Path(__file__).parents[2]
++
+ 
+ class Network(torch.nn.Module):
+     def __init__(self):
+@@ -64,7 +68,7 @@ class Network(torch.nn.Module):
+             torch.nn.Sigmoid()
+         )
+ 
+-        self.load_state_dict({strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.load('./annotator/ckpts/network-bsds500.pth').items()})
++        self.load_state_dict({strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.load(f'{root_dir}/annotator/ckpts/network-bsds500.pth').items()})
+     # end
+ 
+     def forward(self, tenInput):
+diff --git a/annotator/midas/api.py b/annotator/midas/api.py
+index 9fa305e..d8594ea 100644
+--- a/annotator/midas/api.py
++++ b/annotator/midas/api.py
+@@ -1,5 +1,7 @@
+ # based on https://github.com/isl-org/MiDaS
+ 
++import pathlib
++
+ import cv2
+ import torch
+ import torch.nn as nn
+@@ -10,10 +12,11 @@ from .midas.midas_net import MidasNet
+ from .midas.midas_net_custom import MidasNet_small
+ from .midas.transforms import Resize, NormalizeImage, PrepareForNet
+ 
++root_dir = pathlib.Path(__file__).parents[2]
+ 
+ ISL_PATHS = {
+-    "dpt_large": "annotator/ckpts/dpt_large-midas-2f21e586.pt",
+-    "dpt_hybrid": "annotator/ckpts/dpt_hybrid-midas-501f0c75.pt",
++    "dpt_large": f"{root_dir}/annotator/ckpts/dpt_large-midas-2f21e586.pt",
++    "dpt_hybrid": f"{root_dir}/annotator/ckpts/dpt_hybrid-midas-501f0c75.pt",
+     "midas_v21": "",
+     "midas_v21_small": "",
+ }
+diff --git a/annotator/mlsd/__init__.py b/annotator/mlsd/__init__.py
+index 75db717..f310fe6 100644
+--- a/annotator/mlsd/__init__.py
++++ b/annotator/mlsd/__init__.py
+@@ -1,3 +1,5 @@
++import pathlib
++
+ import cv2
+ import numpy as np
+ import torch
+@@ -8,8 +10,9 @@ from .models.mbv2_mlsd_tiny import  MobileV2_MLSD_Tiny
+ from .models.mbv2_mlsd_large import  MobileV2_MLSD_Large
+ from .utils import  pred_lines
+ 
++root_dir = pathlib.Path(__file__).parents[2]
+ 
+-model_path = './annotator/ckpts/mlsd_large_512_fp32.pth'
++model_path = f'{root_dir}/annotator/ckpts/mlsd_large_512_fp32.pth'
+ model = MobileV2_MLSD_Large()
+ model.load_state_dict(torch.load(model_path), strict=True)
+ model = model.cuda().eval()
+diff --git a/annotator/openpose/__init__.py b/annotator/openpose/__init__.py
+index 47d50a5..2369eed 100644
+--- a/annotator/openpose/__init__.py
++++ b/annotator/openpose/__init__.py
+@@ -1,4 +1,5 @@
+ import os
++import pathlib
+ os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
+ 
+ import torch
+@@ -7,8 +8,10 @@ from . import util
+ from .body import Body
+ from .hand import Hand
+ 
+-body_estimation = Body('./annotator/ckpts/body_pose_model.pth')
+-hand_estimation = Hand('./annotator/ckpts/hand_pose_model.pth')
++root_dir = pathlib.Path(__file__).parents[2]
++
++body_estimation = Body(f'{root_dir}/annotator/ckpts/body_pose_model.pth')
++hand_estimation = Hand(f'{root_dir}/annotator/ckpts/hand_pose_model.pth')
+ 
+ 
+ def apply_openpose(oriImg, hand=False):
+diff --git a/annotator/uniformer/__init__.py b/annotator/uniformer/__init__.py
+index 500e53c..4061dbe 100644
+--- a/annotator/uniformer/__init__.py
++++ b/annotator/uniformer/__init__.py
+@@ -1,9 +1,12 @@
++import pathlib
++
+ from annotator.uniformer.mmseg.apis import init_segmentor, inference_segmentor, show_result_pyplot
+ from annotator.uniformer.mmseg.core.evaluation import get_palette
+ 
++root_dir = pathlib.Path(__file__).parents[2]
+ 
+-checkpoint_file = "annotator/ckpts/upernet_global_small.pth"
+-config_file = 'annotator/uniformer/exp/upernet_global_small/config.py'
++checkpoint_file = f"{root_dir}/annotator/ckpts/upernet_global_small.pth"
++config_file = f'{root_dir}/annotator/uniformer/exp/upernet_global_small/config.py'
+ model = init_segmentor(config_file, checkpoint_file).cuda()
+ 
+ 
+diff --git a/annotator/util.py b/annotator/util.py
+index 7cde937..10a6d58 100644
+--- a/annotator/util.py
++++ b/annotator/util.py
+@@ -25,7 +25,7 @@ def resize_image(input_image, resolution):
+     H, W, C = input_image.shape
+     H = float(H)
+     W = float(W)
+-    k = float(resolution) / min(H, W)
++    k = float(resolution) / max(H, W)
+     H *= k
+     W *= k
+     H = int(np.round(H / 64.0)) * 64

requirements.txt

@@ -0,0 +1,22 @@
+addict==2.4.0
+albumentations==1.3.0
+einops==0.6.0
+git+https://github.com/huggingface/accelerate@78151f8
+git+https://github.com/huggingface/diffusers@fa6d52d
+gradio==3.23.0
+imageio==2.25.0
+imageio-ffmpeg==0.4.8
+kornia==0.6.9
+omegaconf==2.3.0
+open-clip-torch==2.13.0
+opencv-contrib-python==4.7.0.68
+opencv-python-headless==4.7.0.68
+prettytable==3.6.0
+pytorch-lightning==1.9.0
+safetensors==0.2.8
+timm==0.6.12
+torch==1.13.1
+torchvision==0.14.1
+transformers==4.26.1
+xformers==0.0.16
+yapf==0.32.0

style.css

@@ -0,0 +1,8 @@
+h1 {
+  text-align: center;
+}
+
+.note {
+  text-align: center;
+  font-size: 150%;
+}