#135 · Primary category: Computer Vision
ComfyUI-RMBG
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.
Project last updated:08/21/26
GitHub Stars
2.1K
Forks
133
Contributors
3
License
GPL-3.0
Why we included this project
People who cut images in ComfyUI often end up stringing together separate scripts. This node pack bundles a broad set of segmentation models, including RMBG-2.0, BEN and BEN2, BiRefNet, SDMatte, SAM, SAM2, SAM3, GroundingDINO, and INSPYRENET, so the cutting work lives inside your workflow instead of outside it. It handles background stripping, hair and transparent object matting, and isolating faces, clothing, or fashion items without custom code. Text-prompted segmentation through SAM2 and GroundingDINO is useful when you want one specific object rather than everything in frame. The pack also includes mask combine and enhance, object removal, image stitching, and real-time background replacement, turning it into a general editing toolbox. Teams already using ComfyUI for product photography, e-commerce prep, or retouching will likely find most masking needs covered with a single install.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)