Files
MoonHugo-ComfyUI-BiRefNet-Hugo/README.md
T
2024-09-21 18:11:58 +08:00

2.8 KiB
Raw Blame History

ComfyUI-BiRefNet-Hugo

介绍 | Introduction

本仓库将BiRefNet最新模型封装为ComfyUI节点来使用,相较于旧模型,最新模型的抠图精度更高更好。
This repository wraps the latest BiRefNet model as ComfyUI nodes. Compared to the previous model, the latest model offers higher and better matting accuracy.

安装 | Installation

  1. 进入节点目录, ComfyUI/custom_nodes/
  2. git clone https://github.com/MoonHugo/ComfyUI-BiRefNet-Hugo.git
  3. cd ComfyUI-BiRefNet-Hugo
  4. pip install -r requirements.txt

  1. Go to comfyUI custom_nodes folder, ComfyUI/custom_nodes/
  2. git clone https://github.com/MoonHugo/ComfyUI-BiRefNet-Hugo.git
  3. cd ComfyUI-BiRefNet-Hugo
  4. pip install -r requirements.txt

使用 | Usage

示例工作流放置在ComfyUI-BiRefNet-Hugo/workflow中
The demo workflow placed in ComfyUI-BiRefNet-Hugo/workflow

加载模型支持两种方式,一种是自动下载远程模型并加载模型,另外一种是加载本地模型。加载本地模型的时候需要把load_local_model设置为true,并把local_model_path设置为本地模型所在路径,例如:H:\ZhengPeng7\BiRefNet
Loading the model supports two methods: one is to automatically download and load a remote model, and the other is to load a local model. When loading a local model, you need to set 'load_local_model' to true and 'local_model_path' to the path where the local model is located, for example: H:\ZhengPeng7\BiRefNet.

模型下载地址:https://huggingface.co/ZhengPeng7/BiRefNet/tree/main
Model download address: https://huggingface.co/ZhengPeng7/BiRefNet/tree/main


工作流workflow.json的使用
The use of workflow.json

plot

工作流video_workflow.json的使用
The use of video_workflow.json


plot

效果演示 | Sample Result

社交账号 | Social Account Homepage

感谢 | Acknowledgments

感谢BiRefNet仓库的所有作者 ZhengPeng7/BiRefNet

Thanks to BiRefNet repo owner ZhengPeng7/BiRefNet

部分代码参考了 ZHO-ZHO-ZHO/ComfyUI-BiRefNet-ZHO 感谢!

Some of the code references ZHO-ZHO-ZHO/ComfyUI-BiRefNet-ZHO Thanks!

关注历史 | star history

Star History Chart