Duplicate from hysts/ControlNet

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

.gitattributes

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

.gitignore

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

.gitmodules

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

.pre-commit-config.yaml

@@ -0,0 +1,37 @@
+exclude: patch
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.2.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: double-quote-string-fixer
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ['--fix=lf']
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.4
+  hooks:
+  - id: docformatter
+    args: ['--in-place']
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.991
+  hooks:
+    - id: mypy
+      args: ['--ignore-missing-imports']
+      additional_dependencies: ['types-python-slugify']
+- repo: https://github.com/google/yapf
+  rev: v0.32.0
+  hooks:
+  - id: yapf
+    args: ['--parallel', '--in-place']

.style.yapf

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

ControlNet

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

LICENSE.ControlNet

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,14 @@
+---
+title: ControlNet
+emoji: 🌖
+colorFrom: pink
+colorTo: blue
+sdk: gradio
+sdk_version: 3.18.0
+python_version: 3.10.9
+app_file: app.py
+pinned: false
+duplicated_from: hysts/ControlNet
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import os
+import pathlib
+import shlex
+import subprocess
+
+import gradio as gr
+
+if os.getenv('SYSTEM') == 'spaces':
+    with open('patch') as f:
+        subprocess.run(shlex.split('patch -p1'), stdin=f, cwd='ControlNet')
+
+base_url = 'https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/'
+names = [
+    'body_pose_model.pth',
+    'dpt_hybrid-midas-501f0c75.pt',
+    'hand_pose_model.pth',
+    'mlsd_large_512_fp32.pth',
+    'mlsd_tiny_512_fp32.pth',
+    'network-bsds500.pth',
+    'upernet_global_small.pth',
+]
+for name in names:
+    command = f'wget https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/{name} -O {name}'
+    out_path = pathlib.Path(f'ControlNet/annotator/ckpts/{name}')
+    if out_path.exists():
+        continue
+    subprocess.run(shlex.split(command), cwd='ControlNet/annotator/ckpts/')
+
+from gradio_canny2image import create_demo as create_demo_canny
+from gradio_depth2image import create_demo as create_demo_depth
+from gradio_fake_scribble2image import create_demo as create_demo_fake_scribble
+from gradio_hed2image import create_demo as create_demo_hed
+from gradio_hough2image import create_demo as create_demo_hough
+from gradio_normal2image import create_demo as create_demo_normal
+from gradio_pose2image import create_demo as create_demo_pose
+from gradio_scribble2image import create_demo as create_demo_scribble
+from gradio_scribble2image_interactive import \
+    create_demo as create_demo_scribble_interactive
+from gradio_seg2image import create_demo as create_demo_seg
+from model import Model
+
+MAX_IMAGES = 1
+DESCRIPTION = '''# ControlNet
+
+This is an unofficial demo for [https://github.com/lllyasviel/ControlNet](https://github.com/lllyasviel/ControlNet).
+
+If you are interested in trying out other base models, check out [this Space](https://huggingface.co/spaces/hysts/ControlNet-with-other-models) as well.
+'''
+if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
+    DESCRIPTION += f'''<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings.<br/>
+<a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true">
+<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
+<p/>
+'''
+
+model = Model()
+
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(DESCRIPTION)
+    with gr.Tabs():
+        with gr.TabItem('Canny'):
+            create_demo_canny(model.process_canny, max_images=MAX_IMAGES)
+        with gr.TabItem('Hough'):
+            create_demo_hough(model.process_hough, max_images=MAX_IMAGES)
+        with gr.TabItem('HED'):
+            create_demo_hed(model.process_hed, max_images=MAX_IMAGES)
+        with gr.TabItem('Scribble'):
+            create_demo_scribble(model.process_scribble, max_images=MAX_IMAGES)
+        with gr.TabItem('Scribble Interactive'):
+            create_demo_scribble_interactive(
+                model.process_scribble_interactive, max_images=MAX_IMAGES)
+        with gr.TabItem('Fake Scribble'):
+            create_demo_fake_scribble(model.process_fake_scribble,
+                                      max_images=MAX_IMAGES)
+        with gr.TabItem('Pose'):
+            create_demo_pose(model.process_pose, max_images=MAX_IMAGES)
+        with gr.TabItem('Segmentation'):
+            create_demo_seg(model.process_seg, max_images=MAX_IMAGES)
+        with gr.TabItem('Depth'):
+            create_demo_depth(model.process_depth, max_images=MAX_IMAGES)
+        with gr.TabItem('Normal map'):
+            create_demo_normal(model.process_normal, max_images=MAX_IMAGES)
+
+demo.queue(api_open=False).launch()

gradio_canny2image.py

@@ -0,0 +1,75 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_canny2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Canny Edge Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    low_threshold = gr.Slider(label='Canny low threshold',
+                                              minimum=1,
+                                              maximum=255,
+                                              value=100,
+                                              step=1)
+                    high_threshold = gr.Slider(label='Canny high threshold',
+                                               minimum=1,
+                                               maximum=255,
+                                               value=200,
+                                               step=1)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, ddim_steps, scale, seed, eta, low_threshold,
+            high_threshold
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='canny')
+    return demo

gradio_depth2image.py

@@ -0,0 +1,69 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_depth2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Depth Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='Depth Resolution',
+                                                  minimum=128,
+                                                  maximum=1024,
+                                                  value=384,
+                                                  step=1)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed, eta
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='depth')
+    return demo

gradio_fake_scribble2image.py

@@ -0,0 +1,69 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_fake_scribble2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Fake Scribble Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='HED Resolution',
+                                                  minimum=128,
+                                                  maximum=1024,
+                                                  value=512,
+                                                  step=1)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed, eta
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='fake_scribble')
+    return demo

gradio_hed2image.py

@@ -0,0 +1,69 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_hed2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with HED Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='HED Resolution',
+                                                  minimum=128,
+                                                  maximum=1024,
+                                                  value=512,
+                                                  step=1)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed, eta
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='hed')
+    return demo

gradio_hough2image.py

@@ -0,0 +1,82 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_hough2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Hough Line Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='Hough Resolution',
+                                                  minimum=128,
+                                                  maximum=1024,
+                                                  value=512,
+                                                  step=1)
+                    value_threshold = gr.Slider(
+                        label='Hough value threshold (MLSD)',
+                        minimum=0.01,
+                        maximum=2.0,
+                        value=0.1,
+                        step=0.01)
+                    distance_threshold = gr.Slider(
+                        label='Hough distance threshold (MLSD)',
+                        minimum=0.01,
+                        maximum=20.0,
+                        value=0.1,
+                        step=0.01)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed, eta,
+            value_threshold, distance_threshold
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='hough')
+    return demo

gradio_normal2image.py

@@ -0,0 +1,76 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_normal2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Normal Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='Normal Resolution',
+                                                  minimum=128,
+                                                  maximum=1024,
+                                                  value=384,
+                                                  step=1)
+                    bg_threshold = gr.Slider(
+                        label='Normal background threshold',
+                        minimum=0.0,
+                        maximum=1.0,
+                        value=0.4,
+                        step=0.01)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed, eta,
+            bg_threshold
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='normal')
+    return demo

gradio_pose2image.py

@@ -0,0 +1,69 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_pose2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Human Pose')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(label='OpenPose Resolution',
+                                                  minimum=128,
+                                                  maximum=1024,
+                                                  value=512,
+                                                  step=1)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed, eta
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='pose')
+    return demo

gradio_scribble2image.py

@@ -0,0 +1,64 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_scribble2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Scribble Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, ddim_steps, scale, seed, eta
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='scribble')
+    return demo

gradio_scribble2image_interactive.py

@@ -0,0 +1,90 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_scribble2image_interactive.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+import numpy as np
+
+
+def create_canvas(w, h):
+    return np.zeros(shape=(h, w, 3), dtype=np.uint8) + 255
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown(
+                '## Control Stable Diffusion with Interactive Scribbles')
+        with gr.Row():
+            with gr.Column():
+                canvas_width = gr.Slider(label='Canvas Width',
+                                         minimum=256,
+                                         maximum=1024,
+                                         value=512,
+                                         step=1)
+                canvas_height = gr.Slider(label='Canvas Height',
+                                          minimum=256,
+                                          maximum=1024,
+                                          value=512,
+                                          step=1)
+                create_button = gr.Button(label='Start',
+                                          value='Open drawing canvas!')
+                input_image = gr.Image(source='upload',
+                                       type='numpy',
+                                       tool='sketch')
+                gr.Markdown(
+                    value=
+                    'Do not forget to change your brush width to make it thinner. (Gradio do not allow developers to set brush width so you need to do it manually.) '
+                    'Just click on the small pencil icon in the upper right corner of the above block.'
+                )
+                create_button.click(fn=create_canvas,
+                                    inputs=[canvas_width, canvas_height],
+                                    outputs=[input_image],
+                                    queue=False)
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, ddim_steps, scale, seed, eta
+        ]
+        run_button.click(fn=process, inputs=ips, outputs=[result_gallery])
+    return demo

gradio_seg2image.py

@@ -0,0 +1,70 @@
+# This file is adapted from https://github.com/lllyasviel/ControlNet/blob/f4748e3630d8141d7765e2bd9b1e348f47847707/gradio_seg2image.py
+# The original license file is LICENSE.ControlNet in this repo.
+import gradio as gr
+
+
+def create_demo(process, max_images=12):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown('## Control Stable Diffusion with Segmentation Maps')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type='numpy')
+                prompt = gr.Textbox(label='Prompt')
+                run_button = gr.Button(label='Run')
+                with gr.Accordion('Advanced options', open=False):
+                    num_samples = gr.Slider(label='Images',
+                                            minimum=1,
+                                            maximum=max_images,
+                                            value=1,
+                                            step=1)
+                    image_resolution = gr.Slider(label='Image Resolution',
+                                                 minimum=256,
+                                                 maximum=768,
+                                                 value=512,
+                                                 step=256)
+                    detect_resolution = gr.Slider(
+                        label='Segmentation Resolution',
+                        minimum=128,
+                        maximum=1024,
+                        value=512,
+                        step=1)
+                    ddim_steps = gr.Slider(label='Steps',
+                                           minimum=1,
+                                           maximum=100,
+                                           value=20,
+                                           step=1)
+                    scale = gr.Slider(label='Guidance Scale',
+                                      minimum=0.1,
+                                      maximum=30.0,
+                                      value=9.0,
+                                      step=0.1)
+                    seed = gr.Slider(label='Seed',
+                                     minimum=-1,
+                                     maximum=2147483647,
+                                     step=1,
+                                     randomize=True,
+                                     queue=False)
+                    eta = gr.Number(label='eta (DDIM)', value=0.0)
+                    a_prompt = gr.Textbox(
+                        label='Added Prompt',
+                        value='best quality, extremely detailed')
+                    n_prompt = gr.Textbox(
+                        label='Negative Prompt',
+                        value=
+                        'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
+                    )
+            with gr.Column():
+                result_gallery = gr.Gallery(label='Output',
+                                            show_label=False,
+                                            elem_id='gallery').style(
+                                                grid=2, height='auto')
+        ips = [
+            input_image, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed, eta
+        ]
+        run_button.click(fn=process,
+                         inputs=ips,
+                         outputs=[result_gallery],
+                         api_name='seg')
+    return demo

model.py

@@ -0,0 +1,766 @@
+# This file is adapted from gradio_*.py in https://github.com/lllyasviel/ControlNet/tree/f4748e3630d8141d7765e2bd9b1e348f47847707
+# The original license file is LICENSE.ControlNet in this repo.
+from __future__ import annotations
+
+import pathlib
+import random
+import shlex
+import subprocess
+import sys
+
+import cv2
+import einops
+import numpy as np
+import torch
+from pytorch_lightning import seed_everything
+
+sys.path.append('ControlNet')
+
+import config
+from annotator.canny import apply_canny
+from annotator.hed import apply_hed, nms
+from annotator.midas import apply_midas
+from annotator.mlsd import apply_mlsd
+from annotator.openpose import apply_openpose
+from annotator.uniformer import apply_uniformer
+from annotator.util import HWC3, resize_image
+from cldm.model import create_model, load_state_dict
+from ldm.models.diffusion.ddim import DDIMSampler
+from share import *
+
+ORIGINAL_MODEL_NAMES = {
+    'canny': 'control_sd15_canny.pth',
+    'hough': 'control_sd15_mlsd.pth',
+    'hed': 'control_sd15_hed.pth',
+    'scribble': 'control_sd15_scribble.pth',
+    'pose': 'control_sd15_openpose.pth',
+    'seg': 'control_sd15_seg.pth',
+    'depth': 'control_sd15_depth.pth',
+    'normal': 'control_sd15_normal.pth',
+}
+ORIGINAL_WEIGHT_ROOT = 'https://huggingface.co/lllyasviel/ControlNet/resolve/main/models/'
+
+LIGHTWEIGHT_MODEL_NAMES = {
+    'canny': 'control_canny-fp16.safetensors',
+    'hough': 'control_mlsd-fp16.safetensors',
+    'hed': 'control_hed-fp16.safetensors',
+    'scribble': 'control_scribble-fp16.safetensors',
+    'pose': 'control_openpose-fp16.safetensors',
+    'seg': 'control_seg-fp16.safetensors',
+    'depth': 'control_depth-fp16.safetensors',
+    'normal': 'control_normal-fp16.safetensors',
+}
+LIGHTWEIGHT_WEIGHT_ROOT = 'https://huggingface.co/webui/ControlNet-modules-safetensors/resolve/main/'
+
+
+class Model:
+    def __init__(self,
+                 model_config_path: str = 'ControlNet/models/cldm_v15.yaml',
+                 model_dir: str = 'models',
+                 use_lightweight: bool = True):
+        self.device = torch.device(
+            'cuda:0' if torch.cuda.is_available() else 'cpu')
+        self.model = create_model(model_config_path).to(self.device)
+        self.ddim_sampler = DDIMSampler(self.model)
+        self.task_name = ''
+
+        self.model_dir = pathlib.Path(model_dir)
+        self.model_dir.mkdir(exist_ok=True, parents=True)
+
+        self.use_lightweight = use_lightweight
+        if use_lightweight:
+            self.model_names = LIGHTWEIGHT_MODEL_NAMES
+            self.weight_root = LIGHTWEIGHT_WEIGHT_ROOT
+            base_model_url = 'https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors'
+            self.load_base_model(base_model_url)
+        else:
+            self.model_names = ORIGINAL_MODEL_NAMES
+            self.weight_root = ORIGINAL_WEIGHT_ROOT
+
+        self.download_models()
+
+    def download_base_model(self, model_url: str) -> pathlib.Path:
+        model_name = model_url.split('/')[-1]
+        out_path = self.model_dir / model_name
+        if not out_path.exists():
+            subprocess.run(shlex.split(f'wget {model_url} -O {out_path}'))
+        return out_path
+
+    def load_base_model(self, model_url: str) -> None:
+        model_path = self.download_base_model(model_url)
+        self.model.load_state_dict(load_state_dict(model_path,
+                                                   location=self.device.type),
+                                   strict=False)
+
+    def load_weight(self, task_name: str) -> None:
+        if task_name == self.task_name:
+            return
+        weight_path = self.get_weight_path(task_name)
+        if not self.use_lightweight:
+            self.model.load_state_dict(
+                load_state_dict(weight_path, location=self.device))
+        else:
+            self.model.control_model.load_state_dict(
+                load_state_dict(weight_path, location=self.device.type))
+        self.task_name = task_name
+
+    def get_weight_path(self, task_name: str) -> str:
+        if 'scribble' in task_name:
+            task_name = 'scribble'
+        return f'{self.model_dir}/{self.model_names[task_name]}'
+
+    def download_models(self) -> None:
+        self.model_dir.mkdir(exist_ok=True, parents=True)
+        for name in self.model_names.values():
+            out_path = self.model_dir / name
+            if out_path.exists():
+                continue
+            subprocess.run(
+                shlex.split(f'wget {self.weight_root}{name} -O {out_path}'))
+
+    @torch.inference_mode()
+    def process_canny(self, input_image, prompt, a_prompt, n_prompt,
+                      num_samples, image_resolution, ddim_steps, scale, seed,
+                      eta, low_threshold, high_threshold):
+        self.load_weight('canny')
+
+        img = resize_image(HWC3(input_image), image_resolution)
+        H, W, C = img.shape
+
+        detected_map = apply_canny(img, low_threshold, high_threshold)
+        detected_map = HWC3(detected_map)
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [255 - detected_map] + results
+
+    @torch.inference_mode()
+    def process_hough(self, input_image, prompt, a_prompt, n_prompt,
+                      num_samples, image_resolution, detect_resolution,
+                      ddim_steps, scale, seed, eta, value_threshold,
+                      distance_threshold):
+        self.load_weight('hough')
+
+        input_image = HWC3(input_image)
+        detected_map = apply_mlsd(resize_image(input_image, detect_resolution),
+                                  value_threshold, distance_threshold)
+        detected_map = HWC3(detected_map)
+        img = resize_image(input_image, image_resolution)
+        H, W, C = img.shape
+
+        detected_map = cv2.resize(detected_map, (W, H),
+                                  interpolation=cv2.INTER_NEAREST)
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [
+            255 - cv2.dilate(detected_map,
+                             np.ones(shape=(3, 3), dtype=np.uint8),
+                             iterations=1)
+        ] + results
+
+    @torch.inference_mode()
+    def process_hed(self, input_image, prompt, a_prompt, n_prompt, num_samples,
+                    image_resolution, detect_resolution, ddim_steps, scale,
+                    seed, eta):
+        self.load_weight('hed')
+
+        input_image = HWC3(input_image)
+        detected_map = apply_hed(resize_image(input_image, detect_resolution))
+        detected_map = HWC3(detected_map)
+        img = resize_image(input_image, image_resolution)
+        H, W, C = img.shape
+
+        detected_map = cv2.resize(detected_map, (W, H),
+                                  interpolation=cv2.INTER_LINEAR)
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [detected_map] + results
+
+    @torch.inference_mode()
+    def process_scribble(self, input_image, prompt, a_prompt, n_prompt,
+                         num_samples, image_resolution, ddim_steps, scale,
+                         seed, eta):
+        self.load_weight('scribble')
+
+        img = resize_image(HWC3(input_image), image_resolution)
+        H, W, C = img.shape
+
+        detected_map = np.zeros_like(img, dtype=np.uint8)
+        detected_map[np.min(img, axis=2) < 127] = 255
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [255 - detected_map] + results
+
+    @torch.inference_mode()
+    def process_scribble_interactive(self, input_image, prompt, a_prompt,
+                                     n_prompt, num_samples, image_resolution,
+                                     ddim_steps, scale, seed, eta):
+        self.load_weight('scribble')
+
+        img = resize_image(HWC3(input_image['mask'][:, :, 0]),
+                           image_resolution)
+        H, W, C = img.shape
+
+        detected_map = np.zeros_like(img, dtype=np.uint8)
+        detected_map[np.min(img, axis=2) > 127] = 255
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [255 - detected_map] + results
+
+    @torch.inference_mode()
+    def process_fake_scribble(self, input_image, prompt, a_prompt, n_prompt,
+                              num_samples, image_resolution, detect_resolution,
+                              ddim_steps, scale, seed, eta):
+        self.load_weight('scribble')
+
+        input_image = HWC3(input_image)
+        detected_map = apply_hed(resize_image(input_image, detect_resolution))
+        detected_map = HWC3(detected_map)
+        img = resize_image(input_image, image_resolution)
+        H, W, C = img.shape
+
+        detected_map = cv2.resize(detected_map, (W, H),
+                                  interpolation=cv2.INTER_LINEAR)
+        detected_map = nms(detected_map, 127, 3.0)
+        detected_map = cv2.GaussianBlur(detected_map, (0, 0), 3.0)
+        detected_map[detected_map > 4] = 255
+        detected_map[detected_map < 255] = 0
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [255 - detected_map] + results
+
+    @torch.inference_mode()
+    def process_pose(self, input_image, prompt, a_prompt, n_prompt,
+                     num_samples, image_resolution, detect_resolution,
+                     ddim_steps, scale, seed, eta):
+        self.load_weight('pose')
+
+        input_image = HWC3(input_image)
+        detected_map, _ = apply_openpose(
+            resize_image(input_image, detect_resolution))
+        detected_map = HWC3(detected_map)
+        img = resize_image(input_image, image_resolution)
+        H, W, C = img.shape
+
+        detected_map = cv2.resize(detected_map, (W, H),
+                                  interpolation=cv2.INTER_NEAREST)
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [detected_map] + results
+
+    @torch.inference_mode()
+    def process_seg(self, input_image, prompt, a_prompt, n_prompt, num_samples,
+                    image_resolution, detect_resolution, ddim_steps, scale,
+                    seed, eta):
+        self.load_weight('seg')
+
+        input_image = HWC3(input_image)
+        detected_map = apply_uniformer(
+            resize_image(input_image, detect_resolution))
+        img = resize_image(input_image, image_resolution)
+        H, W, C = img.shape
+
+        detected_map = cv2.resize(detected_map, (W, H),
+                                  interpolation=cv2.INTER_NEAREST)
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [detected_map] + results
+
+    @torch.inference_mode()
+    def process_depth(self, input_image, prompt, a_prompt, n_prompt,
+                      num_samples, image_resolution, detect_resolution,
+                      ddim_steps, scale, seed, eta):
+        self.load_weight('depth')
+
+        input_image = HWC3(input_image)
+        detected_map, _ = apply_midas(
+            resize_image(input_image, detect_resolution))
+        detected_map = HWC3(detected_map)
+        img = resize_image(input_image, image_resolution)
+        H, W, C = img.shape
+
+        detected_map = cv2.resize(detected_map, (W, H),
+                                  interpolation=cv2.INTER_LINEAR)
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [detected_map] + results
+
+    @torch.inference_mode()
+    def process_normal(self, input_image, prompt, a_prompt, n_prompt,
+                       num_samples, image_resolution, detect_resolution,
+                       ddim_steps, scale, seed, eta, bg_threshold):
+        self.load_weight('normal')
+
+        input_image = HWC3(input_image)
+        _, detected_map = apply_midas(resize_image(input_image,
+                                                   detect_resolution),
+                                      bg_th=bg_threshold)
+        detected_map = HWC3(detected_map)
+        img = resize_image(input_image, image_resolution)
+        H, W, C = img.shape
+
+        detected_map = cv2.resize(detected_map, (W, H),
+                                  interpolation=cv2.INTER_LINEAR)
+
+        control = torch.from_numpy(
+            detected_map[:, :, ::-1].copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        cond = {
+            'c_concat': [control],
+            'c_crossattn': [
+                self.model.get_learned_conditioning(
+                    [prompt + ', ' + a_prompt] * num_samples)
+            ]
+        }
+        un_cond = {
+            'c_concat': [control],
+            'c_crossattn':
+            [self.model.get_learned_conditioning([n_prompt] * num_samples)]
+        }
+        shape = (4, H // 8, W // 8)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=True)
+
+        samples, intermediates = self.ddim_sampler.sample(
+            ddim_steps,
+            num_samples,
+            shape,
+            cond,
+            verbose=False,
+            eta=eta,
+            unconditional_guidance_scale=scale,
+            unconditional_conditioning=un_cond)
+
+        if config.save_memory:
+            self.model.low_vram_shift(is_diffusing=False)
+
+        x_samples = self.model.decode_first_stage(samples)
+        x_samples = (
+            einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 +
+            127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+        return [detected_map] + results

patch

@@ -0,0 +1,115 @@
+diff --git a/annotator/hed/__init__.py b/annotator/hed/__init__.py
+index 42d8dc6..1587035 100644
+--- a/annotator/hed/__init__.py
++++ b/annotator/hed/__init__.py
+@@ -1,8 +1,12 @@
++import pathlib
++
+ import numpy as np
+ import cv2
+ import torch
+ from einops import rearrange
+ 
++root_dir = pathlib.Path(__file__).parents[2]
++
+ 
+ class Network(torch.nn.Module):
+     def __init__(self):
+@@ -64,7 +68,7 @@ class Network(torch.nn.Module):
+             torch.nn.Sigmoid()
+         )
+ 
+-        self.load_state_dict({strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.load('./annotator/ckpts/network-bsds500.pth').items()})
++        self.load_state_dict({strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.load(f'{root_dir}/annotator/ckpts/network-bsds500.pth').items()})
+     # end
+ 
+     def forward(self, tenInput):
+diff --git a/annotator/midas/api.py b/annotator/midas/api.py
+index 9fa305e..d8594ea 100644
+--- a/annotator/midas/api.py
++++ b/annotator/midas/api.py
+@@ -1,5 +1,7 @@
+ # based on https://github.com/isl-org/MiDaS
+ 
++import pathlib
++
+ import cv2
+ import torch
+ import torch.nn as nn
+@@ -10,10 +12,11 @@ from .midas.midas_net import MidasNet
+ from .midas.midas_net_custom import MidasNet_small
+ from .midas.transforms import Resize, NormalizeImage, PrepareForNet
+ 
++root_dir = pathlib.Path(__file__).parents[2]
+ 
+ ISL_PATHS = {
+-    "dpt_large": "annotator/ckpts/dpt_large-midas-2f21e586.pt",
+-    "dpt_hybrid": "annotator/ckpts/dpt_hybrid-midas-501f0c75.pt",
++    "dpt_large": f"{root_dir}/annotator/ckpts/dpt_large-midas-2f21e586.pt",
++    "dpt_hybrid": f"{root_dir}/annotator/ckpts/dpt_hybrid-midas-501f0c75.pt",
+     "midas_v21": "",
+     "midas_v21_small": "",
+ }
+diff --git a/annotator/mlsd/__init__.py b/annotator/mlsd/__init__.py
+index 75db717..f310fe6 100644
+--- a/annotator/mlsd/__init__.py
++++ b/annotator/mlsd/__init__.py
+@@ -1,3 +1,5 @@
++import pathlib
++
+ import cv2
+ import numpy as np
+ import torch
+@@ -8,8 +10,9 @@ from .models.mbv2_mlsd_tiny import  MobileV2_MLSD_Tiny
+ from .models.mbv2_mlsd_large import  MobileV2_MLSD_Large
+ from .utils import  pred_lines
+ 
++root_dir = pathlib.Path(__file__).parents[2]
+ 
+-model_path = './annotator/ckpts/mlsd_large_512_fp32.pth'
++model_path = f'{root_dir}/annotator/ckpts/mlsd_large_512_fp32.pth'
+ model = MobileV2_MLSD_Large()
+ model.load_state_dict(torch.load(model_path), strict=True)
+ model = model.cuda().eval()
+diff --git a/annotator/openpose/__init__.py b/annotator/openpose/__init__.py
+index 47d50a5..2369eed 100644
+--- a/annotator/openpose/__init__.py
++++ b/annotator/openpose/__init__.py
+@@ -1,4 +1,5 @@
+ import os
++import pathlib
+ os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
+ 
+ import torch
+@@ -7,8 +8,10 @@ from . import util
+ from .body import Body
+ from .hand import Hand
+ 
+-body_estimation = Body('./annotator/ckpts/body_pose_model.pth')
+-hand_estimation = Hand('./annotator/ckpts/hand_pose_model.pth')
++root_dir = pathlib.Path(__file__).parents[2]
++
++body_estimation = Body(f'{root_dir}/annotator/ckpts/body_pose_model.pth')
++hand_estimation = Hand(f'{root_dir}/annotator/ckpts/hand_pose_model.pth')
+ 
+ 
+ def apply_openpose(oriImg, hand=False):
+diff --git a/annotator/uniformer/__init__.py b/annotator/uniformer/__init__.py
+index 500e53c..4061dbe 100644
+--- a/annotator/uniformer/__init__.py
++++ b/annotator/uniformer/__init__.py
+@@ -1,9 +1,12 @@
++import pathlib
++
+ from annotator.uniformer.mmseg.apis import init_segmentor, inference_segmentor, show_result_pyplot
+ from annotator.uniformer.mmseg.core.evaluation import get_palette
+ 
++root_dir = pathlib.Path(__file__).parents[2]
+ 
+-checkpoint_file = "annotator/ckpts/upernet_global_small.pth"
+-config_file = 'annotator/uniformer/exp/upernet_global_small/config.py'
++checkpoint_file = f"{root_dir}/annotator/ckpts/upernet_global_small.pth"
++config_file = f'{root_dir}/annotator/uniformer/exp/upernet_global_small/config.py'
+ model = init_segmentor(config_file, checkpoint_file).cuda()
+ 
+ 

requirements.txt

@@ -0,0 +1,20 @@
+addict==2.4.0
+albumentations==1.3.0
+einops==0.6.0
+gradio==3.18.0
+imageio==2.25.0
+imageio-ffmpeg==0.4.8
+kornia==0.6.9
+omegaconf==2.3.0
+open-clip-torch==2.13.0
+opencv-contrib-python==4.7.0.68
+opencv-python-headless==4.7.0.68
+prettytable==3.6.0
+pytorch-lightning==1.9.0
+safetensors==0.2.8
+timm==0.6.12
+torch==1.13.1
+torchvision==0.14.1
+transformers==4.26.1
+xformers==0.0.16
+yapf==0.32.0

style.css

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