Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

daviduebler/ComfyUI-RMBG

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

359 Commits

Repository files navigation

ComfyUI-RMBG

A sophisticated ComfyUI custom node engineered for advanced image background removal and precise segmentation of objects, faces, clothing, and fashion elements. This tool leverages a diverse array of models, including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet, SDMatte models, SAM, SAM2 and GroundingDINO, while also incorporating a new feature for real-time background replacement and enhanced edge detection for improved accuracy.

News & Updates

  • 2025年12月09日: Update ComfyUI-RMBG to v2.9.6 ( update.md ) v2.9.6_Image Compare

  • 2025年11月25日: Update ComfyUI-RMBG to v2.9.5 SAM3 Segmentaion bug fixed( update.md )

  • 2025年11月24日: Update ComfyUI-RMBG to v2.9.4 SAM3 Segmentaion ( update.md ) v2.9.4_sam3

  • 2025年10月05日: Update ComfyUI-RMBG to v2.9.3 ( update.md ) v2.9._color

  • 2025年09月30日: Update ComfyUI-RMBG to v2.9.2 ( update.md )

  • Add new BiRefNet_toonOut Model v2.9.2_BiRefNet_toonOut

  • Updated Imagestitch v2.9.2_imagestitch

  • 2025年09月12日: Update ComfyUI-RMBG to v2.9.1 ( update.md ) v2.9.1

  • 2025年08月18日: Update ComfyUI-RMBG to v2.9.0 ( update.md ) v2 9 0

    • Added SDMatte Matting node

  • 2025年08月11日: Update ComfyUI-RMBG to v2.8.0 ( update.md ) v2 8 0

    • Added SAM2Segment node for text-prompted segmentation with the latest Facebook Research SAM2 technology.
    • Enhanced color widget support across all nodes

  • 2025年08月06日: Update ComfyUI-RMBG to v2.7.1 ( update.md ) v2.7.0_ImageStitch

    • Enhanced LoadImage into three distinct nodes to meet different needs, all supporting direct image loading from local paths or URLs
    • Completely redesigned ImageStitch node compatible with ComfyUI's native functionality
    • Fixed background color handling issues reported by users

  • 2025年07月15日: Update ComfyUI-RMBG to v2.6.0 ( update.md )

ReferenceLatentMaskr

  • Added Kontext Refence latent Mask node, Which uses a reference latent and mask for precise region conditioning.

  • 2025年07月11日: Update ComfyUI-RMBG to v2.5.2 ( update.md )

V 2 5 2

  • 2025年07月07日: Update ComfyUI-RMBG to v2.5.1 ( update.md )

  • 2025年07月01日: Update ComfyUI-RMBG to v2.5.0 ( update.md )

mask_overlay

  • Added MaskOverlay, ObjectRemover, ImageMaskResize new nodes.

  • Added 2 BiRefNet models: BiRefNet_lite-matting and BiRefNet_dynamic

  • Added batch image support for Segment_v1 and Segment_V2 nodes

  • 2025年06月01日: Update ComfyUI-RMBG to v2.4.0 ( update.md ) ComfyUI-RMBG_V2 4 0 new nodes

    • Added CropObject, ImageCompare, ColorInput nodes and new Segment V2 (see update.md for details)

  • 2025年05月15日: Update ComfyUI-RMBG to v2.3.2 ( update.md ) v 2 3 2

  • 2025年05月02日: Update ComfyUI-RMBG to v2.3.1 ( update.md )

  • 2025年05月01日: Update ComfyUI-RMBG to v2.3.0 ( update.md ) v2 3 0_node

    • Added new nodes: IC-LoRA Concat, Image Crop
    • Added resizing options for Load Image: Longest Side, Shortest Side, Width, and Height, enhancing flexibility.

  • 2025年04月05日: Update ComfyUI-RMBG to v2.2.1 ( update.md )

  • 2025年04月05日: Update ComfyUI-RMBG to v2.2.0 ( update.md ) Comfyu-rmbg_v2 2 1_node_sample

    • Added new nodes: Image Combiner, Image Stitch, Image/Mask Converter, Mask Enhancer, Mask Combiner, and Mask Extractor
    • Fixed compatibility issues with transformers v4.49+
    • Fixed i18n translation errors
    • Added mask image output to segment nodes

  • 2025年03月21日: Update ComfyUI-RMBG to v2.1.1 ( update.md )

    • Enhanced compatibility with Transformers

  • 2025年03月19日: Update ComfyUI-RMBG to v2.1.0 ( update.md )

    • Integrated internationalization (i18n) support for multiple languages.
    • Improved user interface for dynamic language switching.
    • Enhanced accessibility for non-English speaking users with fully translatable features.
ComfyUI-rmbg_i18n.mp4

  • 2025年03月13日: Update ComfyUI-RMBG to v2.0.0 ( update.md ) image_mask_preview

    • Added Image and Mask Tools improved functionality.
    • Enhanced code structure and documentation for better usability.
    • Introduced a new category path: 🧪AILab/🛠️UTIL/🖼️IMAGE.

  • 2025年02月24日: Update ComfyUI-RMBG to v1.9.3 Clean up the code and fix the issue ( update.md )

  • 2025年02月21日: Update ComfyUI-RMBG to v1.9.2 with Fast Foreground Color Estimation ( update.md ) RMBG_V1 9 2

    • Added new foreground refinement feature for better transparency handling
    • Improved edge quality and detail preservation
    • Enhanced memory optimization

  • 2025年02月20日: Update ComfyUI-RMBG to v1.9.1 ( update.md )

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

  • 2025年02月19日: Update ComfyUI-RMBG to v1.9.0 with BiRefNet model improvements ( update.md ) rmbg_v1 9 0

    • Enhanced BiRefNet model performance and stability
    • Improved memory management for large images

  • 2025年02月07日: Update ComfyUI-RMBG to v1.8.0 with new BiRefNet-HR model ( update.md ) RMBG-v1 8 0

    • Added a new custom node for BiRefNet-HR model.
    • Support high resolution image processing (up to 2048x2048)

  • 2025年02月04日: Update ComfyUI-RMBG to v1.7.0 with new BEN2 model ( update.md ) rmbg_v1 7 0

    • Added a new custom node for BEN2 model.

  • 2025年01月22日: Update ComfyUI-RMBG to v1.6.0 with new Face Segment custom node ( update.md ) RMBG_v1 6 0

    • 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

  • 2025年01月05日: Update ComfyUI-RMBG to v1.5.0 with new Fashion and accessories Segment custom node ( update.md ) RMBGv_1 5 0

    • Added a new custom node for fashion segmentation.

  • 2025年01月02日: Update ComfyUI-RMBG to v1.4.0 with new Clothes Segment node ( update.md ) rmbg_v1 4 0

    • Added intelligent clothes segmentation with 18 different categories
    • Support multiple item selection and combined segmentation
    • Same parameter controls as other RMBG nodes

  • 2024年12月29日: Update ComfyUI-RMBG to v1.3.2 with background handling ( update.md )

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

  • 2024年12月25日: Update ComfyUI-RMBG to v1.3.1 with bug fixes ( update.md )

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

  • 2024年12月23日: Update ComfyUI-RMBG to v1.3.0 with new Segment node ( update.md ) rmbg v1.3.0

    • Added text-prompted object segmentation
    • Support both tag-style ("cat, dog") and natural language ("a person wearing red jacket") prompts
    • Multiple models: SAM (vit_h/l/b) and GroundingDINO (SwinT/B) (as always model file will be downloaded automatically when first time using the specific model)
    • This update requires install requirements.txt

  • 2024年12月12日: Update Comfyui-RMBG ComfyUI Custom Node to v1.2.2 ( update.md ) RMBG1 2 2

  • 2024年12月02日: Update Comfyui-RMBG ComfyUI Custom Node to v1.2.1 ( update.md ) GIF_TO_AWEBP

  • 2024年11月29日: Update Comfyui-RMBG ComfyUI Custom Node to v1.2.0 ( update.md ) RMBGv1 2 0

  • 2024年11月21日: Update Comfyui-RMBG ComfyUI Custom Node to v1.1.0 ( update.md ) comfyui-rmbg version compare

Features

  • Background Removal (RMBG Node)

    • Multiple models: RMBG-2.0, INSPYRENET, BEN, BEN2
    • Various background options
    • Batch processing support

  • Object Segmentation (Segment Node)

    • Text-prompted object detection
    • Support both tag-style and natural language inputs
    • High-precision segmentation with SAM
    • Flexible parameter controls

  • SAM2 Segmentation

    • Text-prompted segmentation with the latest SAM2 models (Tiny/Small/Base+/Large)
    • Automatic model download on first use, with manual download option

RMBG Demo

Installation

Method 1. install on ComfyUI-Manager, search Comfyui-RMBG and install

install requirment.txt in the ComfyUI-RMBG folder

./ComfyUI/python_embeded/python -m pip install -r requirements.txt

Tip

Note: If your environment cannot install dependencies with the system Python, you can use ComfyUI's embedded Python instead. Example (embedded Python): ./ComfyUI/python_embeded/python.exe -m pip install --no-user --no-cache-dir -r requirements.txt

Method 2. Clone this repository to your ComfyUI custom_nodes folder:

cd ComfyUI/custom_nodes
git clone https://github.com/1038lab/ComfyUI-RMBG

install requirment.txt in the ComfyUI-RMBG folder

./ComfyUI/python_embeded/python -m pip install -r requirements.txt

Method 3: Install via Comfy CLI

Ensure pip install comfy-cli is installed. Installing ComfyUI comfy install (if you don't have ComfyUI Installed) install the ComfyUI-RMBG, use the following command:

comfy node install ComfyUI-RMBG

install requirment.txt in the ComfyUI-RMBG folder

./ComfyUI/python_embeded/python -m pip install -r requirements.txt

4. Manually download the models:

  • The model will be automatically downloaded to ComfyUI/models/RMBG/ when first time using the custom node.
  • Manually download the RMBG-2.0 model by visiting this link, then download the files and place them in the /ComfyUI/models/RMBG/RMBG-2.0 folder.
  • Manually download the INSPYRENET models by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/INSPYRENET folder.
  • Manually download the BEN model by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/BEN folder.
  • Manually download the BEN2 model by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/BEN2 folder.
  • Manually download the BiRefNet-HR by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/BiRefNet-HR folder.
  • Manually download the SAM models by visiting the link, then download the files and place them in the /ComfyUI/models/SAM folder.
  • Manually download the SAM2 models by visiting the link, then download the files (e.g., sam2.1_hiera_tiny.safetensors, sam2.1_hiera_small.safetensors, sam2.1_hiera_base_plus.safetensors, sam2.1_hiera_large.safetensors) and place them in the /ComfyUI/models/sam2 folder.
  • Manually download the GroundingDINO models by visiting the link, then download the files and place them in the /ComfyUI/models/grounding-dino folder.
  • Manually download the Clothes Segment model by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/segformer_clothes folder.
  • Manually download the Fashion Segment model by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/segformer_fashion folder.
  • Manually download BiRefNet models by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/BiRefNet folder.
  • Manually download SDMatte safetensors models by visiting the link, then download the files and place them in the /ComfyUI/models/RMBG/SDMatte folder.

Usage

RMBG Node

RMBG

Optional Settings 💡 Tips

Optional Settings 📝 Description 💡 Tips
Sensitivity Adjusts the strength of mask detection. Higher values result in stricter detection. Default value is 0.5. Adjust based on image complexity; more complex images may require higher sensitivity.
Processing Resolution Controls the processing resolution of the input image, affecting detail and memory usage. Choose a value between 256 and 2048, with a default of 1024. Higher resolutions provide better detail but increase memory consumption.
Mask Blur Controls the amount of blur applied to the mask edges, reducing jaggedness. Default value is 0. Try setting it between 1 and 5 for smoother edge effects.
Mask Offset Allows for expanding or shrinking the mask boundary. Positive values expand the boundary, while negative values shrink it. Default value is 0. Adjust based on the specific image, typically fine-tuning between -10 and 10.
Background Choose output background color Alpha (transparent background) Black, White, Green, Blue, Red
Invert Output Flip mask and image output Invert both image and mask output
Refine Foreground Use Fast Foreground Color Estimation to optimize transparent background Enable for better edge quality and transparency handling
Performance Optimization Properly setting options can enhance performance when processing multiple images. If memory allows, consider increasing process_res and mask_blur values for better results, but be mindful of memory usage.

Basic Usage

  1. Load RMBG (Remove Background) node from the 🧪AILab/🧽RMBG category
  2. Connect an image to the input
  3. Select a model from the dropdown menu
  4. select the parameters as needed (optional)
  5. Get two outputs:
    • IMAGE: Processed image with transparent, black, white, green, blue, or red background
    • MASK: Binary mask of the foreground

Parameters

  • sensitivity: Controls the background removal sensitivity (0.0-1.0)
  • process_res: Processing resolution (512-2048, step 128)
  • mask_blur: Blur amount for the mask (0-64)
  • mask_offset: Adjust mask edges (-20 to 20)
  • background: Choose output background color
  • invert_output: Flip mask and image output
  • optimize: Toggle model optimization

Segment Node

  1. Load Segment (RMBG) node from the 🧪AILab/🧽RMBG category
  2. Connect an image to the input
  3. Enter text prompt (tag-style or natural language)
  4. Select SAM and GroundingDINO models
  5. Adjust parameters as needed:
    • Threshold: 0.25-0.35 for broad detection, 0.45-0.55 for precision
    • Mask blur and offset for edge refinement
    • Background color options

About Models

RMBG-2.0

RMBG-2.0 is is developed by BRIA AI and uses the BiRefNet architecture which includes:

  • High accuracy in complex environments
  • Precise edge detection and preservation
  • Excellent handling of fine details
  • Support for multiple objects in a single image
  • Output Comparison
  • Output with background
  • Batch output for video The model is trained on a diverse dataset of over 15,000 high-quality images, ensuring:
  • Balanced representation across different image types
  • High accuracy in various scenarios
  • Robust performance with complex backgrounds

INSPYRENET

INSPYRENET is specialized in human portrait segmentation, offering:

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

BEN

BEN is robust on various image types, offering:

  • Good balance between speed and accuracy
  • Effective on both simple and complex scenes
  • Suitable for batch processing

BEN2

BEN2 is a more advanced version of BEN, offering:

  • Improved accuracy and speed
  • Better handling of complex scenes
  • Support for more image types
  • Suitable for batch processing

BIREFNET MODELS

BIREFNET is a powerful model for image segmentation, offering:

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

SAM

SAM is a powerful model for object detection and segmentation, offering:

  • High accuracy in complex environments
  • Precise edge detection and preservation
  • Excellent handling of fine details
  • Support for multiple objects in a single image
  • Output Comparison
  • Output with background
  • Batch output for video

SAM2

SAM2 is the latest segmentation model family designed for efficient, high-quality text-prompted segmentation:

  • Multiple sizes: Tiny, Small, Base+, Large
  • Optimized inference with strong accuracy
  • Automatic download on first use; manual placement supported in ComfyUI/models/sam2

GroundingDINO

GroundingDINO is a model for text-prompted object detection and segmentation, offering:

  • High accuracy in complex environments
  • Precise edge detection and preservation
  • Excellent handling of fine details
  • Support for multiple objects in a single image
  • Output Comparison
  • Output with background
  • Batch output for video

BiRefNet Models

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

Requirements

  • ComfyUI
  • Python 3.10+
  • Required packages (automatically installed):
    • huggingface-hub>=0.19.0
    • transparent-background>=1.1.2
    • segment-anything>=1.0
    • groundingdino-py>=0.4.0
    • opencv-python>=4.7.0
    • onnxruntime>=1.15.0
    • onnxruntime-gpu>=1.15.0
    • protobuf>=3.20.2,<6.0.0
    • hydra-core>=1.3.0
    • omegaconf>=2.3.0
    • iopath>=0.1.9

SDMatte models (manual download)

  • Auto-download on first run to models/RMBG/SDMatte/
  • If network restricted, place weights manually:
    • models/RMBG/SDMatte/SDMatte.safetensors (standard) or SDMatte_plus.safetensors (plus)
    • Components (config files) are auto-downloaded; if needed, mirror the structure from the Hugging Face repo to models/RMBG/SDMatte/ (scheduler/, text_encoder/, tokenizer/, unet/, vae/)

Troubleshooting (short)

  • 401 error when initializing GroundingDINO / missing models/sam2:
    • Delete %USERPROFILE%\.cache\huggingface\token (and %USERPROFILE%\.huggingface\token if present)
    • Ensure no HF_TOKEN/HUGGINGFACE_TOKEN env vars are set
    • Re-run; public repos download anonymously (no login required)
  • Preview shows "Required input is missing: images":
    • Ensure image outputs are connected and upstream nodes ran successfully

Credits

Star History

Star History Chart

If this custom node helps you or you like my work, please give me ⭐ on this repo! It's a great encouragement for my efforts!

License

GPL-3.0 License

About

A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet, SDMatte, SAM, SAM2, SAM3 and GroundingDINO.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

Contributors

Languages

  • Python 99.6%
  • JavaScript 0.4%

AltStyle によって変換されたページ (->オリジナル) /