ComfyUI-RemoveBackgroundSuite

ComfyUI-RemoveBackgroundSuite
★ 7

抠图多模型支持细节处理ComfyUI 插件
基于 ComfyUI 的抠图工具集，支持多种抠图模型与细节处理节点，便于在工作流程中高效生成并优化前景蒙版。
💡 在 ComfyUI 中快速抠图并精细化前景蒙版。
🍴 1 Forks💻 Python🔄 2025-10-25
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/51137d50651f
📦 requirements.txt
--extra-index-url
https://download.pytorch.org/whl/cu118
torch==2.0.1
--extra-index-url
https://download.pytorch.org/whl/cu118
torchvision==0.15.2
numpy<2
opencv-python
timm
scipy
scikit-image
kornia
tqdm
prettytable
huggingface_hub
📄 README

ComfyUI-RemoveBackgroundSuite

版本: v1.2.4

ComfyUI 插件: 抠图工具包

A matting toolkit based on ComfyUI, supporting multiple matting models and detail processing methods.

🆕 最新更新 (v1.2.4)

  • 更新ComfyUI Registry配置: 优化了pyproject.toml配置文件，符合最新的ComfyUI Registry发布规范
  • 完善依赖管理: 同步更新了requirements.txt文件，确保所有依赖项完整
  • 增强元数据: 添加了更详细的标签和描述信息，提升在Registry中的可发现性
  • 图标支持: 配置了项目图标URL，提升用户体验

    • v1.2.3

  • 自动修复BiRefNet兼容性问题: 新增动态配置修复功能，自动解决BiRefNet模型与transformers库的兼容性问题
  • 无需手动修改: 用户安装插件后无需修改models文件夹中的任何文件
  • 智能检测: 自动检测并修复所有BiRefNet模型版本的配置问题
  • 向后兼容: 完全兼容现有工作流程，不影响原始模型文件

    • Features

  • Multiple Models: Support for various matting models including BiRefNet, RMBG, and more
  • Detail Processing: Advanced mask processing capabilities for fine-tuning results
  • User-Friendly: Simple and intuitive interface within ComfyUI
  • High Performance: Optimized for both quality and speed

    • Installation

  • Navigate to your ComfyUI’s custom_nodes directory
  • Clone this repository:
    • git clone https://github.com/whmc76/ComfyUI-RemoveBackgroundSuite.git
  • Install dependencies:
    • cd ComfyUI-RemoveBackgroundSuite
pip install -r requirements.txt

    Usage

  • Start ComfyUI
  • The new nodes will appear in the node menu under the “RBS” category
  • Connect the nodes as needed in your workflow

    • Models

    The following models are supported:

  • BiRefNet-General
  • BiRefNet_dynamic
  • BiRefNet_HR
  • BiRefNet_HR-matting
  • RMBG-2.0

    • Nodes

    BiRefNetUltra_RBS

  • Input: Image
  • Output: Mask
  • Parameters:
  • Model Version: Select from available BiRefNet models
  • Max Megapixels: Maximum image size for processing

    • Transparent Background Ultra (RBS)

  • Input: Image
  • Output: Transparent Image
  • Parameters:
  • Model Version: Select from available models
  • Max Megapixels: Maximum image size for processing

    • Mask Process Details (RBS)

  • Input: Mask
  • Output: Processed Mask
  • Parameters:
  • Detail Method: Choose from VITMatte, PyMatting, or GuidedFilter
  • Erode/Dilate: Control the trimap generation
  • Black/White Point: Adjust mask levels
  • Max Megapixels: Control processing resolution

    • Changelog

    v1.2.1

  • 完善了ComfyUI插件配置和元数据
  • 添加了详细的插件描述和功能标签
  • 优化了README.md的版本信息显示
  • 改进了ComfyUI Registry的兼容性

    • v1.2.0

  • 为 BiRefNet Ultra (RBS) 和 Transparent Background Ultra (RBS) 节点添加了 mask 输入功能
  • 新增 “自动适用原图遮罩” 参数，支持智能检测和使用输入的 mask
  • 优化了节点名称，移除了 BiRefNetUltraV3_RBS 中的 “V3” 后缀
  • 修复了输入 mask 应用时的翻转问题，确保输出结果正确
  • 改进了批量处理逻辑，支持图像和 mask 的自动匹配

    • v1.1.2

  • 修复了模型加载路径的问题
  • 改进了模型自动下载功能
  • 添加了缺失的依赖项
  • 优化了错误处理和日志记录

    • v1.1.1

  • Fixed VITMatte processing quality issues
  • Optimized image size handling for different processing methods
  • Improved mask processing workflow

    • v1.1.0

  • Optimized dependency management
  • Removed version constraints for better compatibility
  • Removed unused dependencies
  • Improved code organization

    • v1.0.0

  • Initial release with core functionality
  • Support for multiple matting models
  • Basic mask processing capabilities

    • License

    This project is licensed under the MIT License – see the LICENSE file for details.

    Acknowledgments

  • ComfyUI for the amazing framework
  • BiRefNet for the matting models
  • RMBG for the background removal model