/ComfyUI_M3Net

comfyui的m3net插件,m3net是不错的显著性检测模型,抠图上效果不错,我开源了一个训练的电商的模型,供大家试玩

Primary LanguagePython

ComfyUI nodes to use M3net

https://github.com/I2-Multimedia-Lab/M3Net

image

Install

  • 推荐使用管理器 ComfyUI Manager 安装(On the Way)

  • 手动安装:

    1. cd custom_nodes
    2. git clone https://github.com/leeguandong/ComfyUI_M3Net.git
    3. 重启 ComfyUI

Use

  • Pre-calculated saliency maps: M3Net-R [uqsr], M3Net-S [6jyh]\
    Pre-trained weights: M3Net-R [m789], M3Net-S [4wnw] 将权重下载到'/custom_nodes/ComfyUI_M3Net/weights'
    我自己也开源了一个权重,链接:https://pan.baidu.com/s/1RxVNP2GHgrCEbM5fKj4ZnQ?pwd=vi01 提取码:vi01,一个一般的训练版本,还有更强的版本,在电商场景上应该比很多模型都强了,==

  • 节点:

    • M3Net Model Loader:自动加载 M3Net 模型
    • M3Net Interface:去除背景

Stars

Star History Chart