Add files

.gitignore

@@ -0,0 +1,162 @@
+gradio_cached_examples/
+
+# 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/

.pre-commit-config.yaml

@@ -0,0 +1,36 @@
+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']

.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

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

@@ -1,13 +1,14 @@
 ---
-title: ControlNet V1 1
+title: ControlNet V1.1
 emoji: 📉
 colorFrom: yellow
 colorTo: green
 sdk: gradio
-sdk_version: 3.24.1
+sdk_version: 3.26.0
+python_version: 3.10.11
 app_file: app.py
 pinned: false
-license: other
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,132 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import os
+
+import gradio as gr
+import torch
+
+from app_canny import create_demo as create_demo_canny
+from app_depth import create_demo as create_demo_depth
+from app_ip2p import create_demo as create_demo_ip2p
+from app_lineart import create_demo as create_demo_lineart
+from app_mlsd import create_demo as create_demo_mlsd
+from app_normal import create_demo as create_demo_normal
+from app_openpose import create_demo as create_demo_openpose
+from app_scribble import create_demo as create_demo_scribble
+from app_scribble_interactive import \
+    create_demo as create_demo_scribble_interactive
+from app_segmentation import create_demo as create_demo_segmentation
+from app_shuffle import create_demo as create_demo_shuffle
+from app_softedge import create_demo as create_demo_softedge
+from model import Model
+
+DESCRIPTION = '# ControlNet v1.1'
+
+SPACE_ID = os.getenv('SPACE_ID')
+ALLOW_CHANGING_BASE_MODEL = SPACE_ID != 'hysts/ControlNet-v1-1'
+
+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>'
+else:
+    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.'
+
+MAX_NUM_IMAGES = int(os.getenv('MAX_NUM_IMAGES', '3'))
+DEFAULT_NUM_IMAGES = min(MAX_NUM_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_NUM_IMAGES,
+                              default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('MLSD'):
+            create_demo_mlsd(model.process_mlsd,
+                             max_images=MAX_NUM_IMAGES,
+                             default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Scribble'):
+            create_demo_scribble(model.process_scribble,
+                                 max_images=MAX_NUM_IMAGES,
+                                 default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Scribble Interactive'):
+            create_demo_scribble_interactive(
+                model.process_scribble_interactive,
+                max_images=MAX_NUM_IMAGES,
+                default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('SoftEdge'):
+            create_demo_softedge(model.process_softedge,
+                                 max_images=MAX_NUM_IMAGES,
+                                 default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('OpenPose'):
+            create_demo_openpose(model.process_openpose,
+                                 max_images=MAX_NUM_IMAGES,
+                                 default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Segmentation'):
+            create_demo_segmentation(model.process_segmentation,
+                                     max_images=MAX_NUM_IMAGES,
+                                     default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Depth'):
+            create_demo_depth(model.process_depth,
+                              max_images=MAX_NUM_IMAGES,
+                              default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Normal map'):
+            create_demo_normal(model.process_normal,
+                               max_images=MAX_NUM_IMAGES,
+                               default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Lineart'):
+            create_demo_lineart(model.process_lineart,
+                                max_images=MAX_NUM_IMAGES,
+                                default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Content Shuffle'):
+            create_demo_shuffle(model.process_shuffle,
+                                max_images=MAX_NUM_IMAGES,
+                                default_num_images=DEFAULT_NUM_IMAGES)
+        with gr.TabItem('Instruct Pix2Pix'):
+            create_demo_ip2p(model.process_ip2p,
+                             max_images=MAX_NUM_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>'''
+            )
+
+    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 +1,106 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Number of 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='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            canny_low_threshold,
+            canny_high_threshold,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='canny',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='Canny')
+    demo = create_demo(model.process_canny)
+    demo.queue().launch()

app_depth.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(
+                        label='Preprocessor',
+                        choices=['Midas', 'DPT', 'None'],
+                        type='value',
+                        value='DPT')
+                    num_samples = gr.Slider(label='Number of 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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=384,
+                        step=1)
+                    num_steps = gr.Slider(label='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='depth',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='depth')
+    demo = create_demo(model.process_depth)
+    demo.queue().launch()

app_ip2p.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Number of 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='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='scribble',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='ip2p')
+    demo = create_demo(model.process_ip2p)
+    demo.queue().launch()

app_lineart.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(
+                        label='Preprocessor',
+                        choices=[
+                            'Lineart',
+                            'Lineart coarse',
+                            'None',
+                            'Lineart (anime)',
+                            'None (anime)',
+                        ],
+                        type='value',
+                        value='Lineart',
+                        info=
+                        'Note that "Lineart (anime)" and "None (anime)" are for anime base models like Anything-v3.'
+                    )
+                    num_samples = gr.Slider(label='Number of 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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=512,
+                        step=1)
+                    num_steps = gr.Slider(label='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='scribble',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='lineart')
+    demo = create_demo(model.process_lineart)
+    demo.queue().launch()

app_mlsd.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Number of 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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess 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='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            mlsd_value_threshold,
+            mlsd_distance_threshold,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='mlsd',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='MLSD')
+    demo = create_demo(model.process_mlsd)
+    demo.queue().launch()

app_normal.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(label='Preprocessor',
+                                                 choices=['NormalBae', 'None'],
+                                                 type='value',
+                                                 value='NormalBae')
+                    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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=384,
+                        step=1)
+                    num_steps = gr.Slider(label='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='normal',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='NormalBae')
+    demo = create_demo(model.process_normal)
+    demo.queue().launch()

app_openpose.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(label='Preprocessor',
+                                                 choices=['Openpose', 'None'],
+                                                 type='value',
+                                                 value='Openpose')
+                    num_samples = gr.Slider(label='Number of 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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=512,
+                        step=1)
+                    num_steps = gr.Slider(label='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='openpose',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='Openpose')
+    demo = create_demo(model.process_openpose)
+    demo.queue().launch()

app_scribble.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(
+                        label='Preprocessor',
+                        choices=['HED', 'PidiNet', 'None'],
+                        type='value',
+                        value='HED')
+                    num_samples = gr.Slider(label='Number of 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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=512,
+                        step=1)
+                    num_steps = gr.Slider(label='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='scribble',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='scribble')
+    demo = create_demo(model.process_scribble)
+    demo.queue().launch()

app_scribble_interactive.py

@@ -0,0 +1,112 @@
+#!/usr/bin/env python
+
+import gradio as gr
+import numpy as np
+
+from utils import randomize_seed_fn
+
+
+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():
+            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('Open drawing canvas!')
+                image = gr.Image(tool='sketch', brush_radius=10)
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Number of 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='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+
+        create_button.click(fn=create_canvas,
+                            inputs=[canvas_width, canvas_height],
+                            outputs=image,
+                            queue=False)
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='scribble')
+    demo = create_demo(model.process_scribble_interactive)
+    demo.queue().launch()

app_segmentation.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(label='Preprocessor',
+                                                 choices=['UPerNet', 'None'],
+                                                 type='value',
+                                                 value='UPerNet')
+                    num_samples = gr.Slider(label='Number of 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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=512,
+                        step=1)
+                    num_steps = gr.Slider(label='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='segmentation',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='segmentation')
+    demo = create_demo(model.process_segmentation)
+    demo.queue().launch()

app_shuffle.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(
+                        label='Preprocessor',
+                        choices=['ContentShuffle', 'None'],
+                        type='value',
+                        value='ContentShuffle')
+                    num_samples = gr.Slider(label='Number of 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='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='content-shuffle',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='shuffle')
+    demo = create_demo(model.process_shuffle)
+    demo.queue().launch()

app_softedge.py

@@ -0,0 +1,110 @@
+#!/usr/bin/env python
+
+import gradio as gr
+
+from utils import randomize_seed_fn
+
+
+def create_demo(process, max_images=12, default_num_images=3):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image()
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button('Run')
+                with gr.Accordion('Advanced options', open=False):
+                    preprocessor_name = gr.Radio(label='Preprocessor',
+                                                 choices=[
+                                                     'HED',
+                                                     'PidiNet',
+                                                     'HED safe',
+                                                     'PidiNet safe',
+                                                     'None',
+                                                 ],
+                                                 type='value',
+                                                 value='PidiNet')
+                    num_samples = gr.Slider(label='Number of 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)
+                    preprocess_resolution = gr.Slider(
+                        label='Preprocess resolution',
+                        minimum=128,
+                        maximum=512,
+                        value=512,
+                        step=1)
+                    num_steps = gr.Slider(label='Number of 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=0,
+                                     maximum=1000000,
+                                     step=1,
+                                     value=0,
+                                     randomize=True)
+                    randomize_seed = gr.Checkbox(label='Randomize seed',
+                                                 value=True)
+                    a_prompt = gr.Textbox(
+                        label='Additional 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).style(
+                    columns=2, object_fit='scale-down')
+        inputs = [
+            image,
+            prompt,
+            a_prompt,
+            n_prompt,
+            num_samples,
+            image_resolution,
+            preprocess_resolution,
+            num_steps,
+            guidance_scale,
+            seed,
+            preprocessor_name,
+        ]
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+        )
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+        ).then(
+            fn=process,
+            inputs=inputs,
+            outputs=result,
+            api_name='scribble',
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    model = Model(task_name='softedge')
+    demo = create_demo(model.process_softedge)
+    demo.queue().launch()

cv_utils.py

@@ -0,0 +1,17 @@
+import cv2
+import numpy as np
+
+
+def resize_image(input_image, resolution, interpolation=None):
+    H, W, C = input_image.shape
+    H = float(H)
+    W = float(W)
+    k = float(resolution) / max(H, W)
+    H *= k
+    W *= k
+    H = int(np.round(H / 64.0)) * 64
+    W = int(np.round(W / 64.0)) * 64
+    if interpolation is None:
+        interpolation = cv2.INTER_LANCZOS4 if k > 1 else cv2.INTER_AREA
+    img = cv2.resize(input_image, (W, H), interpolation=interpolation)
+    return img

depth_estimator.py

@@ -0,0 +1,25 @@
+import numpy as np
+import PIL.Image
+from controlnet_aux.util import HWC3
+from transformers import pipeline
+
+from cv_utils import resize_image
+
+
+class DepthEstimator:
+    def __init__(self):
+        self.model = pipeline('depth-estimation')
+
+    def __call__(self, image: np.ndarray, **kwargs) -> PIL.Image.Image:
+        detect_resolution = kwargs.pop('detect_resolution', 512)
+        image_resolution = kwargs.pop('image_resolution', 512)
+        image = np.array(image)
+        image = HWC3(image)
+        image = resize_image(image, resolution=detect_resolution)
+        image = PIL.Image.fromarray(image)
+        image = self.model(image)
+        image = image['depth']
+        image = np.array(image)
+        image = HWC3(image)
+        image = resize_image(image, resolution=image_resolution)
+        return PIL.Image.fromarray(image)

image_segmentor.py

@@ -0,0 +1,39 @@
+import cv2
+import numpy as np
+import PIL.Image
+import torch
+from controlnet_aux.util import HWC3, ade_palette
+from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
+
+from cv_utils import resize_image
+
+
+class ImageSegmentor:
+    def __init__(self):
+        self.image_processor = AutoImageProcessor.from_pretrained(
+            'openmmlab/upernet-convnext-small')
+        self.image_segmentor = UperNetForSemanticSegmentation.from_pretrained(
+            'openmmlab/upernet-convnext-small')
+
+    @torch.inference_mode()
+    def __call__(self, image: np.ndarray, **kwargs) -> PIL.Image.Image:
+        detect_resolution = kwargs.pop('detect_resolution', 512)
+        image_resolution = kwargs.pop('image_resolution', 512)
+        image = HWC3(image)
+        image = resize_image(image, resolution=detect_resolution)
+        image = PIL.Image.fromarray(image)
+
+        pixel_values = self.image_processor(image,
+                                            return_tensors='pt').pixel_values
+        outputs = self.image_segmentor(pixel_values)
+        seg = self.image_processor.post_process_semantic_segmentation(
+            outputs, target_sizes=[image.size[::-1]])[0]
+        color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8)
+        for label, color in enumerate(ade_palette()):
+            color_seg[seg == label, :] = color
+        color_seg = color_seg.astype(np.uint8)
+
+        color_seg = resize_image(color_seg,
+                                 resolution=image_resolution,
+                                 interpolation=cv2.INTER_NEAREST)
+        return PIL.Image.fromarray(color_seg)

model.py

@@ -0,0 +1,591 @@
+from __future__ import annotations
+
+import gc
+
+import numpy as np
+import PIL.Image
+import torch
+from controlnet_aux.util import HWC3
+from diffusers import (ControlNetModel, DiffusionPipeline,
+                       StableDiffusionControlNetPipeline,
+                       UniPCMultistepScheduler)
+
+from cv_utils import resize_image
+from preprocessor import Preprocessor
+
+CONTROLNET_MODEL_IDS = {
+    'Openpose': 'lllyasviel/control_v11p_sd15_openpose',
+    'Canny': 'lllyasviel/control_v11p_sd15_canny',
+    'MLSD': 'lllyasviel/control_v11p_sd15_mlsd',
+    'scribble': 'lllyasviel/control_v11p_sd15_scribble',
+    'softedge': 'lllyasviel/control_v11p_sd15_softedge',
+    'segmentation': 'lllyasviel/control_v11p_sd15_seg',
+    'depth': 'lllyasviel/control_v11p_sd15_depth',
+    'NormalBae': 'lllyasviel/control_v11p_sd15_normalbae',
+    'lineart': 'lllyasviel/control_v11p_sd15_lineart',
+    'lineart_anime': 'lllyasviel/control_v11p_sd15s2_lineart_anime',
+    'shuffle': 'lllyasviel/control_v11e_sd15_shuffle',
+    'ip2p': 'lllyasviel/control_v11e_sd15_ip2p',
+    'inpaint': 'lllyasviel/control_v11e_sd15_inpaint',
+}
+
+
+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)
+        self.preprocessor = Preprocessor()
+
+    def load_pipe(self, base_model_id: str, task_name) -> DiffusionPipeline:
+        if base_model_id == self.base_model_id and task_name == self.task_name and hasattr(
+                self, 'pipe') and self.pipe is not None:
+            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)
+        if self.device.type == 'cuda':
+            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 self.pipe is not None and hasattr(self.pipe, 'controlnet'):
+            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
+
+    @torch.inference_mode()
+    def process_canny(
+        self,
+        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]:
+        self.preprocessor.load('Canny')
+        control_image = self.preprocessor(image=image,
+                                          low_threshold=low_threshold,
+                                          high_threshold=high_threshold,
+                                          detect_resolution=image_resolution)
+
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_mlsd(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        value_threshold: float,
+        distance_threshold: float,
+    ) -> list[PIL.Image.Image]:
+        self.preprocessor.load('MLSD')
+        control_image = self.preprocessor(
+            image=image,
+            image_resolution=image_resolution,
+            detect_resolution=preprocess_resolution,
+            thr_v=value_threshold,
+            thr_d=distance_threshold,
+        )
+        self.load_controlnet_weight('MLSD')
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_scribble(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name == 'None':
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        elif preprocessor_name == 'HED':
+            self.preprocessor.load(preprocessor_name)
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+                scribble=False,
+            )
+        elif preprocessor_name == 'PidiNet':
+            self.preprocessor.load(preprocessor_name)
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+                safe=False,
+            )
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_scribble_interactive(
+        self,
+        image_and_mask: dict[str, 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]:
+        image = image_and_mask['mask']
+        image = HWC3(image)
+        image = resize_image(image, resolution=image_resolution)
+        control_image = PIL.Image.fromarray(image)
+
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_softedge(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name == 'None':
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        elif preprocessor_name in ['HED', 'HED safe']:
+            safe = 'safe' in preprocessor_name
+            self.preprocessor.load('HED')
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+                scribble=safe,
+            )
+        elif preprocessor_name in ['PidiNet', 'PidiNet safe']:
+            safe = 'safe' in preprocessor_name
+            self.preprocessor.load('PidiNet')
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+                safe=safe,
+            )
+        else:
+            raise ValueError
+        self.load_controlnet_weight('softedge')
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_openpose(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name == 'None':
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        else:
+            self.preprocessor.load('Openpose')
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+                hand_and_face=True,
+            )
+        self.load_controlnet_weight('Openpose')
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_segmentation(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name == 'None':
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        else:
+            self.preprocessor.load(preprocessor_name)
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+            )
+        self.load_controlnet_weight('segmentation')
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_depth(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name == 'None':
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        else:
+            self.preprocessor.load(preprocessor_name)
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+            )
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_normal(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name == 'None':
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        else:
+            self.preprocessor.load('NormalBae')
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+            )
+        self.load_controlnet_weight('NormalBae')
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_lineart(
+        self,
+        image: np.ndarray,
+        prompt: str,
+        additional_prompt: str,
+        negative_prompt: str,
+        num_images: int,
+        image_resolution: int,
+        preprocess_resolution: int,
+        num_steps: int,
+        guidance_scale: float,
+        seed: int,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name in ['None', 'None (anime)']:
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        elif preprocessor_name in ['Lineart', 'Lineart coarse']:
+            coarse = 'coarse' in preprocessor_name
+            self.preprocessor.load('Lineart')
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+                coarse=coarse,
+            )
+        elif preprocessor_name == 'Lineart (anime)':
+            self.preprocessor.load('LineartAnime')
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+                detect_resolution=preprocess_resolution,
+            )
+        if 'anime' in preprocessor_name:
+            self.load_controlnet_weight('lineart_anime')
+        else:
+            self.load_controlnet_weight('lineart')
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_shuffle(
+        self,
+        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,
+        preprocessor_name: str,
+    ) -> list[PIL.Image.Image]:
+        if preprocessor_name == 'None':
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            control_image = PIL.Image.fromarray(image)
+        else:
+            self.preprocessor.load(preprocessor_name)
+            control_image = self.preprocessor(
+                image=image,
+                image_resolution=image_resolution,
+            )
+        self.load_controlnet_weight('shuffle')
+        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 [control_image] + results
+
+    @torch.inference_mode()
+    def process_ip2p(
+        self,
+        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]:
+        image = HWC3(image)
+        image = resize_image(image, resolution=image_resolution)
+        control_image = PIL.Image.fromarray(image)
+        self.load_controlnet_weight('ip2p')
+        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 [control_image] + results

preprocessor.py

@@ -0,0 +1,77 @@
+import gc
+
+import numpy as np
+import PIL.Image
+import torch
+from controlnet_aux import (CannyDetector, ContentShuffleDetector, HEDdetector,
+                            LineartAnimeDetector, LineartDetector,
+                            MidasDetector, MLSDdetector, NormalBaeDetector,
+                            OpenposeDetector, PidiNetDetector)
+from controlnet_aux.util import HWC3
+
+from cv_utils import resize_image
+from depth_estimator import DepthEstimator
+from image_segmentor import ImageSegmentor
+
+
+class Preprocessor:
+    MODEL_ID = 'lllyasviel/Annotators'
+
+    def __init__(self):
+        self.model = None
+        self.name = ''
+
+    def load(self, name: str) -> None:
+        if name == self.name:
+            return
+        if name == 'HED':
+            self.model = HEDdetector.from_pretrained(self.MODEL_ID)
+        elif name == 'Midas':
+            self.model = MidasDetector.from_pretrained(self.MODEL_ID)
+        elif name == 'MLSD':
+            self.model = MLSDdetector.from_pretrained(self.MODEL_ID)
+        elif name == 'Openpose':
+            self.model = OpenposeDetector.from_pretrained(self.MODEL_ID)
+        elif name == 'PidiNet':
+            self.model = PidiNetDetector.from_pretrained(self.MODEL_ID)
+        elif name == 'NormalBae':
+            self.model = NormalBaeDetector.from_pretrained(self.MODEL_ID)
+        elif name == 'Lineart':
+            self.model = LineartDetector.from_pretrained(self.MODEL_ID)
+        elif name == 'LineartAnime':
+            self.model = LineartAnimeDetector.from_pretrained(self.MODEL_ID)
+        elif name == 'Canny':
+            self.model = CannyDetector()
+        elif name == 'ContentShuffle':
+            self.model = ContentShuffleDetector()
+        elif name == 'DPT':
+            self.model = DepthEstimator()
+        elif name == 'UPerNet':
+            self.model = ImageSegmentor()
+        else:
+            raise ValueError
+        torch.cuda.empty_cache()
+        gc.collect()
+        self.name = name
+
+    def __call__(self, image: PIL.Image.Image, **kwargs) -> PIL.Image.Image:
+        if self.name == 'Canny':
+            if 'detect_resolution' in kwargs:
+                detect_resolution = kwargs.pop('detect_resolution')
+                image = np.array(image)
+                image = HWC3(image)
+                image = resize_image(image, resolution=detect_resolution)
+            image = self.model(image, **kwargs)
+            return PIL.Image.fromarray(image)
+        elif self.name == 'Midas':
+            detect_resolution = kwargs.pop('detect_resolution', 512)
+            image_resolution = kwargs.pop('image_resolution', 512)
+            image = np.array(image)
+            image = HWC3(image)
+            image = resize_image(image, resolution=detect_resolution)
+            image = self.model(image, **kwargs)
+            image = HWC3(image)
+            image = resize_image(image, resolution=image_resolution)
+            return PIL.Image.fromarray(image)
+        else:
+            return self.model(image, **kwargs)

requirements.txt

@@ -0,0 +1,12 @@
+accelerate==0.18.0
+controlnet_aux==0.0.3
+diffusers==0.15.0
+einops==0.6.0
+gradio==3.26.0
+huggingface-hub==0.13.4
+opencv-python-headless==4.7.0.72
+safetensors==0.3.0
+torch==2.0.0
+torchvision==0.15.1
+transformers==4.28.1
+xformers==0.0.18

style.css

@@ -0,0 +1,3 @@
+h1 {
+  text-align: center;
+}

utils.py

@@ -0,0 +1,7 @@
+import random
+
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, 1000000)
+    return seed