Duplicate from fffiloni/ControlNet-Video

Co-authored-by: Sylvain Filoni <fffiloni@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-Video
+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: fffiloni/ControlNet-Video
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,244 @@
+from __future__ import annotations
+import gradio as gr
+import os
+import cv2
+import numpy as np
+from PIL import Image
+from moviepy.editor import *
+from share_btn import community_icon_html, loading_icon_html, share_js
+
+import pathlib
+import shlex
+import subprocess
+
+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 model import Model
+model = Model()
+
+
+def controlnet(i, prompt, control_task, seed_in, ddim_steps, scale):
+    img= Image.open(i)
+    np_img = np.array(img)
+    
+    a_prompt = "best quality, extremely detailed"
+    n_prompt = "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"
+    num_samples = 1
+    image_resolution = 512
+    detect_resolution = 512
+    eta = 0.0
+    low_threshold = 100
+    high_threshold = 200
+    
+    if control_task == 'Canny':
+        result = model.process_canny(np_img, prompt, a_prompt, n_prompt, num_samples,
+                image_resolution, ddim_steps, scale, seed_in, eta, low_threshold, high_threshold)
+    elif control_task == 'Depth':
+        result = model.process_depth(np_img, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed_in, eta)
+    elif control_task == 'Pose':
+        result = model.process_pose(np_img, prompt, a_prompt, n_prompt, num_samples,
+            image_resolution, detect_resolution, ddim_steps, scale, seed_in, eta)
+    
+    #print(result[0])
+    im = Image.fromarray(result[1])
+    im.save("your_file" + str(i) + ".jpeg")
+    return "your_file" + str(i) + ".jpeg"
+
+
+def get_frames(video_in):
+    frames = []
+    #resize the video
+    clip = VideoFileClip(video_in)
+    
+    #check fps
+    if clip.fps > 30:
+        print("vide rate is over 30, resetting to 30")
+        clip_resized = clip.resize(height=512)
+        clip_resized.write_videofile("video_resized.mp4", fps=30)
+    else:
+        print("video rate is OK")
+        clip_resized = clip.resize(height=512)
+        clip_resized.write_videofile("video_resized.mp4", fps=clip.fps)
+    
+    print("video resized to 512 height")
+    
+    # Opens the Video file with CV2
+    cap= cv2.VideoCapture("video_resized.mp4")
+    
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    print("video fps: " + str(fps))
+    i=0
+    while(cap.isOpened()):
+        ret, frame = cap.read()
+        if ret == False:
+            break
+        cv2.imwrite('kang'+str(i)+'.jpg',frame)
+        frames.append('kang'+str(i)+'.jpg')
+        i+=1
+    
+    cap.release()
+    cv2.destroyAllWindows()
+    print("broke the video into frames")
+    
+    return frames, fps
+
+
+def create_video(frames, fps):
+    print("building video result")
+    clip = ImageSequenceClip(frames, fps=fps)
+    clip.write_videofile("movie.mp4", fps=fps)
+    
+    return 'movie.mp4'
+
+
+def infer(prompt,video_in, control_task, seed_in, trim_value, ddim_steps, scale):
+    print(f"""
+    ———————————————
+    {prompt}
+    ———————————————""")
+    
+    # 1. break video into frames and get FPS
+    break_vid = get_frames(video_in)
+    frames_list= break_vid[0]
+    fps = break_vid[1]
+    n_frame = int(trim_value*fps)
+    
+    if n_frame >= len(frames_list):
+        print("video is shorter than the cut value")
+        n_frame = len(frames_list)
+    
+    # 2. prepare frames result array
+    result_frames = []
+    print("set stop frames to: " + str(n_frame))
+    
+    for i in frames_list[0:int(n_frame)]:
+        controlnet_img = controlnet(i, prompt,control_task, seed_in, ddim_steps, scale)
+        #images = controlnet_img[0]
+        #rgb_im = images[0].convert("RGB")
+  
+        # exporting the image
+        #rgb_im.save(f"result_img-{i}.jpg")
+        result_frames.append(controlnet_img)
+        print("frame " + i + "/" + str(n_frame) + ": done;")
+
+    final_vid = create_video(result_frames, fps)
+    print("finished !")
+    
+    return final_vid, gr.Group.update(visible=True)
+    #return controlnet_img
+
+title = """
+    <div style="text-align: center; max-width: 700px; margin: 0 auto;">
+        <div
+        style="
+            display: inline-flex;
+            align-items: center;
+            gap: 0.8rem;
+            font-size: 1.75rem;
+        "
+        >
+        <h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
+            ControlNet Video
+        </h1>
+        </div>
+        <p style="margin-bottom: 10px; font-size: 94%">
+        Apply ControlNet to a video 
+        </p>
+    </div>
+"""
+
+article = """
+    
+    <div class="footer">
+        <p>
+        Follow <a href="https://twitter.com/fffiloni" target="_blank">Sylvain Filoni</a> for future updates 🤗
+        </p>
+    </div>
+    <div id="may-like-container" style="display: flex;justify-content: center;flex-direction: column;align-items: center;margin-bottom: 30px;">
+        <p>You may also like: </p>
+        <div id="may-like-content" style="display:flex;flex-wrap: wrap;align-items:center;height:20px;">
+            
+            <svg height="20" width="148" style="margin-left:4px;margin-bottom: 6px;">       
+                 <a href="https://huggingface.co/spaces/fffiloni/Pix2Pix-Video" target="_blank">
+                    <image href="https://img.shields.io/badge/🤗 Spaces-Pix2Pix_Video-blue" src="https://img.shields.io/badge/🤗 Spaces-Pix2Pix_Video-blue.png" height="20"/>
+                 </a>
+            </svg>
+            
+        </div>
+    
+    </div>
+    
+"""
+
+with gr.Blocks(css='style.css') as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(title)
+        with gr.Row():
+            with gr.Column():
+                video_inp = gr.Video(label="Video source", source="upload", type="filepath", elem_id="input-vid")
+                video_out = gr.Video(label="ControlNet video result", elem_id="video-output")
+                with gr.Group(elem_id="share-btn-container", visible=False) as share_group:
+                    community_icon = gr.HTML(community_icon_html)
+                    loading_icon = gr.HTML(loading_icon_html)
+                    share_button = gr.Button("Share to community", elem_id="share-btn")
+            with gr.Column():
+                #status = gr.Textbox()
+                
+                prompt = gr.Textbox(label="Prompt", placeholder="enter prompt", show_label=True, elem_id="prompt-in")
+                control_task = gr.Dropdown(label="Control Task", choices=["Canny", "Depth", "Pose"], value="Pose", multiselect=False)
+                with gr.Row():
+                    seed_inp = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, value=123456)
+                    trim_in = gr.Slider(label="Cut video at (s)", minimun=1, maximum=5, step=1, value=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)
+                
+                submit_btn = gr.Button("Generate ControlNet video")
+                
+                gr.HTML("""
+                <a style="display:inline-block" href="https://huggingface.co/spaces/fffiloni/Pix2Pix-Video?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a> 
+                work with longer videos / skip the queue: 
+                """, elem_id="duplicate-container")
+        
+        inputs = [prompt,video_inp,control_task, seed_inp, trim_in, ddim_steps, scale]
+        outputs = [video_out, share_group]
+        #outputs = [status]
+        
+        
+        gr.HTML(article)
+    
+    submit_btn.click(infer, inputs, outputs)
+    share_button.click(None, [], [], _js=share_js)
+
+    
+    
+demo.queue(max_size=12).launch()

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 +1,23 @@
+opencv-python
+ffmpeg-python
+moviepy
+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

share_btn.py

@@ -0,0 +1,72 @@
+community_icon_html = """<svg id="share-btn-share-icon" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32">
+    <path d="M20.6081 3C21.7684 3 22.8053 3.49196 23.5284 4.38415C23.9756 4.93678 24.4428 5.82749 24.4808 7.16133C24.9674 7.01707 25.4353 6.93643 25.8725 6.93643C26.9833 6.93643 27.9865 7.37587 28.696 8.17411C29.6075 9.19872 30.0124 10.4579 29.8361 11.7177C29.7523 12.3177 29.5581 12.8555 29.2678 13.3534C29.8798 13.8646 30.3306 14.5763 30.5485 15.4322C30.719 16.1032 30.8939 17.5006 29.9808 18.9403C30.0389 19.0342 30.0934 19.1319 30.1442 19.2318C30.6932 20.3074 30.7283 21.5229 30.2439 22.6548C29.5093 24.3704 27.6841 25.7219 24.1397 27.1727C21.9347 28.0753 19.9174 28.6523 19.8994 28.6575C16.9842 29.4379 14.3477 29.8345 12.0653 29.8345C7.87017 29.8345 4.8668 28.508 3.13831 25.8921C0.356375 21.6797 0.754104 17.8269 4.35369 14.1131C6.34591 12.058 7.67023 9.02782 7.94613 8.36275C8.50224 6.39343 9.97271 4.20438 12.4172 4.20438H12.4179C12.6236 4.20438 12.8314 4.2214 13.0364 4.25468C14.107 4.42854 15.0428 5.06476 15.7115 6.02205C16.4331 5.09583 17.134 4.359 17.7682 3.94323C18.7242 3.31737 19.6794 3 20.6081 3ZM20.6081 5.95917C20.2427 5.95917 19.7963 6.1197 19.3039 6.44225C17.7754 7.44319 14.8258 12.6772 13.7458 14.7131C13.3839 15.3952 12.7655 15.6837 12.2086 15.6837C11.1036 15.6837 10.2408 14.5497 12.1076 13.1085C14.9146 10.9402 13.9299 7.39584 12.5898 7.1776C12.5311 7.16799 12.4731 7.16355 12.4172 7.16355C11.1989 7.16355 10.6615 9.33114 10.6615 9.33114C10.6615 9.33114 9.0863 13.4148 6.38031 16.206C3.67434 18.998 3.5346 21.2388 5.50675 24.2246C6.85185 26.2606 9.42666 26.8753 12.0653 26.8753C14.8021 26.8753 17.6077 26.2139 19.1799 25.793C19.2574 25.7723 28.8193 22.984 27.6081 20.6107C27.4046 20.212 27.0693 20.0522 26.6471 20.0522C24.9416 20.0522 21.8393 22.6726 20.5057 22.6726C20.2076 22.6726 19.9976 22.5416 19.9116 22.222C19.3433 20.1173 28.552 19.2325 27.7758 16.1839C27.639 15.6445 27.2677 15.4256 26.746 15.4263C24.4923 15.4263 19.4358 19.5181 18.3759 19.5181C18.2949 19.5181 18.2368 19.4937 18.2053 19.4419C17.6743 18.557 17.9653 17.9394 21.7082 15.6009C25.4511 13.2617 28.0783 11.8545 26.5841 10.1752C26.4121 9.98141 26.1684 9.8956 25.8725 9.8956C23.6001 9.89634 18.2311 14.9403 18.2311 14.9403C18.2311 14.9403 16.7821 16.496 15.9057 16.496C15.7043 16.496 15.533 16.4139 15.4169 16.2112C14.7956 15.1296 21.1879 10.1286 21.5484 8.06535C21.7928 6.66715 21.3771 5.95917 20.6081 5.95917Z" fill="#FF9D00"></path>
+    <path d="M5.50686 24.2246C3.53472 21.2387 3.67446 18.9979 6.38043 16.206C9.08641 13.4147 10.6615 9.33111 10.6615 9.33111C10.6615 9.33111 11.2499 6.95933 12.59 7.17757C13.93 7.39581 14.9139 10.9401 12.1069 13.1084C9.29997 15.276 12.6659 16.7489 13.7459 14.713C14.8258 12.6772 17.7747 7.44316 19.304 6.44221C20.8326 5.44128 21.9089 6.00204 21.5484 8.06532C21.188 10.1286 14.795 15.1295 15.4171 16.2118C16.0391 17.2934 18.2312 14.9402 18.2312 14.9402C18.2312 14.9402 25.0907 8.49588 26.5842 10.1752C28.0776 11.8545 25.4512 13.2616 21.7082 15.6008C17.9646 17.9393 17.6744 18.557 18.2054 19.4418C18.7372 20.3266 26.9998 13.1351 27.7759 16.1838C28.5513 19.2324 19.3434 20.1173 19.9117 22.2219C20.48 24.3274 26.3979 18.2382 27.6082 20.6107C28.8193 22.9839 19.2574 25.7722 19.18 25.7929C16.0914 26.62 8.24723 28.3726 5.50686 24.2246Z" fill="#FFD21E"></path>
+</svg>"""
+
+loading_icon_html = """<svg id="share-btn-loading-icon" style="display:none;" class="animate-spin"
+   style="color: #ffffff; 
+"
+   xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" fill="none" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><circle style="opacity: 0.25;" cx="12" cy="12" r="10" stroke="white" stroke-width="4"></circle><path style="opacity: 0.75;" fill="white" d="M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4zm2 5.291A7.962 7.962 0 014 12H0c0 3.042 1.135 5.824 3 7.938l3-2.647z"></path></svg>"""
+
+share_js = """async () => {
+	async function uploadFile(file){
+		const UPLOAD_URL = 'https://huggingface.co/uploads';
+		const response = await fetch(UPLOAD_URL, {
+			method: 'POST',
+			headers: {
+				'Content-Type': file.type,
+				'X-Requested-With': 'XMLHttpRequest',
+			},
+			body: file, /// <- File inherits from Blob
+		});
+		const url = await response.text();
+		return url;
+	}
+	
+    async function getVideoBlobFile(videoEL){
+        const res = await fetch(videoEL.src);
+        const blob = await res.blob();
+        const videoId = Date.now() % 200;
+        const fileName = `vid-pix2pix-${{videoId}}.wav`;
+        const videoBlob = new File([blob], fileName, { type: 'video/mp4' });
+        console.log(videoBlob);
+        return videoBlob;
+	}
+    
+    const gradioEl = document.querySelector("gradio-app").shadowRoot || document.querySelector('body > gradio-app');
+    const captionTxt = gradioEl.querySelector('#prompt-in textarea').value;
+    const inputVidEl = gradioEl.querySelector('#input-vid video');
+    const outputVideo = gradioEl.querySelector('#video-output video');
+    
+    const shareBtnEl = gradioEl.querySelector('#share-btn');
+    const shareIconEl = gradioEl.querySelector('#share-btn-share-icon');
+    const loadingIconEl = gradioEl.querySelector('#share-btn-loading-icon');
+    if(!outputVideo){
+        return;
+    };
+    shareBtnEl.style.pointerEvents = 'none';
+    shareIconEl.style.display = 'none';
+    loadingIconEl.style.removeProperty('display');
+    
+    const inputFile = await getVideoBlobFile(inputVidEl);
+    const urlInputVid = await uploadFile(inputFile);
+    const videoOutFile = await getVideoBlobFile(outputVideo);
+	const dataOutputVid = await uploadFile(videoOutFile);
+    
+    const descriptionMd = `
+#### Video input:
+${urlInputVid}
+
+#### ControlNet result:
+${dataOutputVid}
+`;
+    const params = new URLSearchParams({
+        title: captionTxt,
+        description: descriptionMd,
+    });
+	const paramsStr = params.toString();
+	window.open(`https://huggingface.co/spaces/fffiloni/ControlNet-Video/discussions/new?${paramsStr}`, '_blank');
+    shareBtnEl.style.removeProperty('pointer-events');
+    shareIconEl.style.removeProperty('display');
+    loadingIconEl.style.display = 'none';
+}"""

style.css

@@ -0,0 +1,101 @@
+#col-container {max-width: 820px; margin-left: auto; margin-right: auto;}
+#duplicate-container{
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  line-height: 1em;
+  flex-direction: row-reverse;
+  font-size:1em;
+}
+a, a:hover, a:visited {
+  text-decoration-line: underline; 
+  font-weight: 600;
+  color: #1f2937 !important;
+}
+
+.dark a, .dark a:hover, .dark a:visited {
+  color: #f3f4f6 !important;
+}
+
+.footer {
+  margin-bottom: 45px;
+  margin-top: 10px;
+  text-align: center;
+  border-bottom: 1px solid #e5e5e5;
+}
+
+.footer>p {
+  font-size: .8rem!important;
+  display: inline-block;
+  padding: 0 10px;
+  transform: translateY(26px);
+  background: white;
+}
+.dark .footer {
+  border-color: #303030;
+}
+.dark .footer>p {
+  background: #0b0f19;
+}
+
+div#may-like-container > p {
+  font-size: .8em;
+  margin-bottom: 4px;
+}
+
+.animate-spin {
+  animation: spin 1s linear infinite;
+}
+
+@keyframes spin {
+  from {
+      transform: rotate(0deg);
+  }
+  to {
+      transform: rotate(360deg);
+  }
+}
+
+#share-btn-container {
+  display: flex; 
+  padding-left: 0.5rem !important; 
+  padding-right: 0.5rem !important; 
+  background-color: #000000; 
+  justify-content: center; 
+  align-items: center; 
+  border-radius: 9999px !important; 
+  max-width: 13rem;
+}
+
+#share-btn-container:hover {
+  background-color: #060606;
+}
+
+#share-btn {
+  all: initial; 
+  color: #ffffff;
+  font-weight: 600; 
+  cursor:pointer; 
+  font-family: 'IBM Plex Sans', sans-serif; 
+  margin-left: 0.5rem !important; 
+  padding-top: 0.5rem !important; 
+  padding-bottom: 0.5rem !important;
+  right:0;
+}
+
+#share-btn * {
+  all: unset;
+}
+
+#share-btn-container div:nth-child(-n+2){
+  width: auto !important;
+  min-height: 0px !important;
+}
+
+#share-btn-container .wrap {
+  display: none !important;
+}
+
+#share-btn-container.hidden {
+  display: none!important;
+}