ComfyUI-Dwpose-Tensorrt

ComfyUI-Dwpose-Tensorrt
★ 52

姿态估计TensorRT 加速ComfyUI 节点实时推理
在 ComfyUI 中提供基于 TensorRT 的 Dwpose 实现，自动构建推理引擎，实现超高速、多帧人体姿态估计，兼顾速度与精度。
💡 在 ComfyUI 中对视频或批量帧进行实时人体姿态估计与加速推理。
🍴 2 Forks💻 Python🔄 2025-05-03
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/6862a2001521
📦 requirements.txt
tensorrt
polygraphy
numpy
tqdm
opencv-python
matplotlib
📄 README

ComfyUI Dwpose TensorRT ⚡

[](https://www.python.org/downloads/release/python-31012/)

[](https://developer.nvidia.com/cuda-downloads)

[](https://developer.nvidia.com/tensorrt)

[](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en)

This project provides a Tensorrt implementation of Dwpose for ultra fast pose estimation inside ComfyUI

⭐ Support

If you like my projects and wish to see updates and new features, please consider supporting me. It helps a lot!

[](https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt)

[](https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt)

[](https://github.com/yuvraj108c/ComfyUI-Dwpose-Tensorrt)

[](https://github.com/yuvraj108c/ComfyUI-Rife-Tensorrt)

[](https://github.com/yuvraj108c/ComfyUI-Whisper)

[](https://github.com/yuvraj108c/ComfyUI_InvSR)

[](https://github.com/yuvraj108c/ComfyUI-Thera)

[](https://github.com/yuvraj108c/ComfyUI-Video-Depth-Anything)

[](https://github.com/yuvraj108c/ComfyUI-PiperTTS)

[](https://www.buymeacoffee.com/yuvraj108cZ)

[](https://paypal.me/yuvraj108c)

⏱️ Performance

_Note: The following results were benchmarked inside ComfyUI, using 1000 similar frames_

| Device | FPS |

| :—-: | :-: |

| L40s | 20 |

| RTX4090 | 18.7 |

🚀 Installation

Navigate to the ComfyUI /custom_nodes directory

git clone https://github.com/yuvraj108c/ComfyUI-Dwpose-Tensorrt
cd ./ComfyUI-Dwpose-Tensorrt
pip install -r requirements.txt

☀️ Usage

  • Insert node by Right Click -> tensorrt -> Dwpose Tensorrt
  • Tensorrt engines will be built automatically
  • Set DWPOSE precision to FP32 for better accuracy

    • 🚨 Updates

    3 May 2025

  • Automatic tensorrt engines are built from the workflow itself, to simplify the process for non-technical people

    • 🤖 Environment tested

  • Ubuntu 22.04 LTS, Cuda 12.4, Tensorrt 10.2.0.post1, Python 3.10, L40s GPU
  • Windows (Not tested, but should work)

    • 👏 Credits

  • https://github.com/IDEA-Research/DWPose
  • https://github.com/legraphista/dwpose-video

    • License

    Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)