1038lab-ComfyUI-RMBG/update.md

ComfyUI-RMBG Update Log

v2.0.0 (2025/03/13)

New Features

• Added Load Image, Preview Image, Preview Mask, and a node that previews both the image and the mask simultaneously. This is the first phase of our toolset, with more useful tools coming in future updates.
• Reorganized the code structure for better maintainability, making it easier to navigate and update.
• Renamed certain node classes to prevent conflicts with other repositories.
• Improved category organization with a new structure: 🧪AILab/🛠️UTIL/🖼️IMAGE, making tools easier to find and use.
• Integrated predefined workflows into the ComfyUI Browse Template section, allowing users to quickly load and understand each custom node’s functionality.

Technical Improvements

• Optimized utility functions for image and mask conversion
• Improved error handling and code robustness
• Updated and changed some variable names for consistency
• Enhanced compatibility with the latest ComfyUI versions

v1.9.3 (2025/02/24)

• Clean up the code and fix the transformers version issue transformers>=4.35.0,<=4.48.3

v1.9.2 (2025/02/21)

New Features

• Added Fast Foreground Color Estimation feature
  • New refine_foreground option for optimizing transparent backgrounds
  • Improved edge quality and detail preservation
  • Better handling of semi-transparent regions

Technical Improvements

• Added OpenCV dependency for advanced image processing
• Enhanced foreground refinement algorithm
• Optimized memory usage for large images
• Improved edge detection accuracy

v1.9.1 (2025/02/20)

Technical Updates

• Changed repository for model management to the new repository
• Reorganized models files structure for better maintainability

v1.9.0 (2025/02/19)

Add and group all BiRefNet models collections into BiRefNet node.

New BiRefNet Models Adds

• Added BiRefNet general purpose model (balanced performance)
• Added BiRefNet_512x512 model (optimized for 512x512 resolution)
• Added BiRefNet-portrait model (optimized for portrait/human matting)
• Added BiRefNet-matting model (general purpose matting)
• Added BiRefNet-HR model (high resolution up to 2560x2560)
• Added BiRefNet-HR-matting model (high resolution matting)
• Added BiRefNet_lite model (lightweight version for faster processing)
• Added BiRefNet_lite-2K model (lightweight version for 2K resolution)

Technical Improvements

• Added FP16 (half-precision) support for better performance
• Optimized for high-resolution image processing
• Enhanced memory efficiency
• Maintained compatibility with existing workflows
• Simplified model loading through Transformers pipeline

v1.8.0 (2025/02/07)

** (To ensure compatibility with the old V1.8.0 workflow, we have replaced this image with the new BiRefNet Node) (2025/03/01)

New Model Added: BiRefNet-HR

• Added support for BiRefNet High Resolution model
• Trained with 2048x2048 resolution images
• Superior performance metrics (maxFm: 0.925, MAE: 0.026)
• Better edge detection and detail preservation
• FP16 optimization for faster processing
• MIT License for commercial use

** (To ensure compatibility with the old V1.8.0 workflow, we have replaced this image with the new BiRefNet Node) (2025/03/01)

Technical Improvements

• Added FP16 (half-precision) support for better performance
• Optimized for high-resolution image processing
• Enhanced memory efficiency
• Maintained compatibility with existing workflows
• Simplified model loading through Transformers pipeline

Performance Comparison

• BiRefNet-HR vs other models:
  • Higher resolution support (up to 2048x2048)
  • Better edge detection accuracy
  • Improved detail preservation
  • Optimized for high-resolution images
  • More efficient memory usage with FP16 support

v1.7.0 (2025/02/05)

New Model Added: BEN2

• Added support for BEN2 (Background Elimination Network 2)
  • Improved performance over original BEN model
  • Better edge detection and detail preservation
  • Enhanced batch processing capabilities (up to 3 images per batch)
  • Optimized memory usage and processing speed

Model Changes

• Updated model repository paths for BEN and BEN2
• Switched to 1038lab repositories for better maintenance and updates
• Maintained full compatibility with existing workflows

Technical Improvements

• Implemented efficient batch processing for BEN2
• Optimized memory management for large batches
• Enhanced error handling and model loading
• Improved model switching and resource cleanup

Comparison with Previous Models

• BEN2 vs BEN:
  • Better edge detection
  • Improved handling of complex backgrounds
  • More efficient batch processing
  • Enhanced detail preservation
  • Faster processing speed

v1.6.0 (2025/01/22)

New Face Segment Custom Node

• Added a new custom node for face parsing and segmentation
  • Support for 19 facial feature categories (Skin, Nose, Eyes, Eyebrows, etc.)
  • Precise facial feature extraction and segmentation
  • Multiple feature selection for combined segmentation
  • Same parameter controls as other RMBG nodes
  • Automatic model downloading and resource management
  • Perfect for portrait editing and facial feature manipulation

v1.5.0 (2025/01/05)

New Fashion and accessories Segment Custom Node

• Added a new custom node for fashion and accessories segmentation.
  • Capable of identifying and segmenting various fashion items such as dresses, shoes, and accessories.
  • Utilizes advanced machine learning techniques for accurate segmentation.
  • Supports real-time processing for enhanced user experience.
  • Ideal for fashion-related applications, including virtual try-ons and outfit recommendations.
  • Support for gray background color.

v1.4.0 (2025/01/02)

New Clothes Segment Node

• Added intelligent clothes segmentation functionality
  • Support for 18 different clothing categories (Hat, Hair, Face, Sunglasses, Upper-clothes, etc.)
  • Multiple item selection for combined segmentation
  • Same parameter controls as other RMBG nodes (process_res, mask_blur, mask_offset, background options)
  • Automatic model downloading and resource management

v1.3.2 (2024/12/29)

Updates

• Enhanced background handling to support RGBA output when "Alpha" is selected.
• Ensured RGB output for all other background color selections.

v1.3.1 (2024/12/25)

Bug Fixes

• Fixed an issue with mask processing when the model returns a list of masks.
• Improved handling of image formats to prevent processing errors.

v1.3.0 (2024/12/23)

New Segment (RMBG) Node

• Text-Prompted Intelligent Object Segmentation
  • Use natural language prompts (e.g., "a cat", "red car") to identify and segment target objects
  • Support for multiple object detection and segmentation
  • Perfect for precise object extraction and recognition tasks

Supported Models

• SAM (Segment Anything Model)
  • sam_vit_h: 2.56GB - Highest accuracy
  • sam_vit_l: 1.25GB - Balanced performance
  • sam_vit_b: 375MB - Lightweight option
• GroundingDINO
  • SwinT: 694MB - Fast and efficient
  • SwinB: 938MB - Higher precision

Key Features

• Intuitive Parameter Controls
  • Threshold: Adjust detection precision
  • Mask Blur: Smooth edges
  • Mask Offset: Expand or shrink selection
  • Background Options: Alpha/Black/White/Green/Blue/Red
• Automatic Model Management
  • Auto-download models on first use
  • Smart GPU memory handling

Usage Examples

1. Tag-Style Prompts

   • Single object: "cat"
   • Multiple objects: "cat, dog, person"
   • With attributes: "red car, blue shirt"
   • Format: Use commas to separate multiple objects (e.g., "a, b, c")

2. Natural Language Prompts

   • Simple sentence: "a person wearing a red jacket"
   • Complex scene: "a woman in a blue dress standing next to a car"
   • With location: "a cat sitting on the sofa"
   • Format: Write a natural descriptive sentence

3. Tips for Better Results

   • For Tag Style:
     • Separate objects with commas: "chair, table, lamp"
     • Add attributes before objects: "wooden chair, glass table"
     • Keep it simple and clear
   • For Natural Language:
     • Use complete sentences
     • Include details like color, position, action
     • Be as descriptive as needed
   • Parameter Adjustments:
     • Threshold: 0.25-0.35 for broad detection, 0.45-0.55 for precision
     • Use mask blur for smoother edges
     • Adjust mask offset to fine-tune selection

v1.2.2 (2024/12/12)

Improvements

• Changed INSPYRENET model format from .pth to .safetensors for:
  • Better security
  • Faster loading speed (2-3x faster)
  • Improved memory efficiency
  • Better cross-platform compatibility
• Simplified node display name for better UI integration

v1.2.1 (2024/12/02)

New Features

• ANPG (animated PNG), AWEBP (animated WebP) and GIF supported.

https://github.com/user-attachments/assets/40ec0b27-4fa2-4c99-9aea-5afad9ca62a5

Bug Fixes

• Fixed video processing issue

Performance Improvements

• Enhanced batch processing in RMBG-2.0 model
• Added support for proper batch image handling
• Improved memory efficiency by optimizing image size handling

Technical Details

• Added original size preservation for maintaining aspect ratios
• Implemented proper batch tensor processing
• Improved error handling and code robustness
• Performance gains:
  • Single image processing: ~5-10% improvement
  • Batch processing: up to 30-50% improvement (depending on batch size and GPU)

v1.2.0 (2024/11/29)

Major Changes

• Combined three background removal models into one unified node
• Added support for RMBG-2.0, INSPYRENET, and BEN models
• Implemented lazy loading for models (only downloads when first used)

Model Introduction

• RMBG-2.0 (Homepage)

  • Latest version of RMBG model
  • Excellent performance on complex backgrounds
  • High accuracy in preserving fine details
  • Best for general purpose background removal

• INSPYRENET (Homepage)

  • Specialized in human portrait segmentation
  • Fast processing speed
  • Good edge detection capability
  • Ideal for portrait photos and human subjects

• BEN (Background Elimination Network) (Homepage)

  • Robust performance on various image types
  • Good balance between speed and accuracy
  • Effective on both simple and complex scenes
  • Suitable for batch processing

Features

• Unified interface for all three models
• Common parameters for all models:
  • Sensitivity adjustment
  • Processing resolution control
  • Mask blur and offset options
  • Multiple background color options
  • Invert output option
  • Model optimization toggle

Improvements

• Optimized memory usage with model clearing
• Enhanced error handling and user feedback
• Added detailed tooltips for all parameters
• Improved mask post-processing

Dependencies

• Updated all package dependencies to latest stable versions
• Added support for transparent-background package
• Optimized dependency management

v1.1.0 (2024/11/21)

New Features

• Added background color options
  • Alpha (transparent background)
  • Black, White, Green, Blue, Red

• Improved mask processing
  • Better detail preservation
  • Enhanced edge quality
  • More accurate segmentation

• Added video batch processing
  • Support for video file background removal
  • Maintains original video framerate and resolution
  • Multiple output format support (with Alpha channel)
  • Efficient batch processing for video frames

https://github.com/user-attachments/assets/259220d3-c148-4030-93d6-c17dd5bccee1

• Added model cache management
  • Cache status checking
  • Model memory cleanup
  • Better error handling

Parameter Updates

• Renamed 'invert_mask' to 'invert_output' for clarity
• Added sensitivity adjustment for mask strength
• Updated tooltips for better clarity

Technical Improvements

• Optimized image processing pipeline
• Added proper model cache verification
• Improved memory management
• Better error handling and recovery
• Enhanced batch processing performance for videos

Dependencies

• Added timm>=0.6.12,<1.0.0 for model support
• Updated requirements.txt with version constraints

Bug Fixes

• Fixed mask detail preservation issues
• Improved mask edge quality
• Fixed memory leaks in model handling

Usage Notes

• The 'Alpha' background option provides transparent background
• Sensitivity parameter now controls mask strength
• Model cache is checked before each operation
• Memory is automatically cleaned when switching models
• Video processing supports various formats and maintains quality