Metadata-Version: 2.4
Name: controlnet_dwpose
Version: 0.1.0
Summary: DWPose component from ControlNeXt for whole-body pose estimation
Home-page: https://github.com/kapong/controlnet_dwpose
Author: P.Phienphanich
Author-email: garpong@gmail.com
Project-URL: Bug Reports, https://github.com/kapong/controlnet_dwpose/issues
Project-URL: Source, https://github.com/kapong/controlnet_dwpose
Project-URL: Original ControlNeXt, https://github.com/dvlab-research/ControlNeXt
Project-URL: Original DWPose, https://github.com/IDEA-Research/DWPose
Keywords: pose-estimation controlnext controllable-generation onnx
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Processing
Classifier: Topic :: Multimedia :: Video
Requires-Python: >=3.10
Description-Content-Type: text/plain
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: opencv-python
Requires-Dist: onnxruntime-gpu
Requires-Dist: torch
Requires-Dist: matplotlib
Requires-Dist: decord
Requires-Dist: tqdm
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: black; extra == "dev"
Requires-Dist: flake8; extra == "dev"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license-file
Dynamic: project-url
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

DWPose is a whole-body pose estimation library extracted and packaged from ControlNeXt project by Peng et al. It provides dense keypoint detection for body, hands, and face using ONNX Runtime. The original DWPose method was developed by Yang et al. (ICCV 2023) and later adapted by Peng et al. for the ControlNeXt controllable generation framework. This package provides a standalone implementation with improved API and documentation.
