#202 · Primary category: Computer Vision
ComfyUI-SAM3
ComfyUI wrapper for segment anything 3
Project last updated:08/24/26
GitHub Stars
569
Forks
81
Contributors
10
License
GPL-3.0
Why we included this project
Meta's SAM3 segmentation model runs inside ComfyUI through this node pack, so you can isolate objects in stills or video by typing a short phrase like "person" or "car" instead of tracing masks by hand. The nodes return segmentation masks and bounding boxes, which covers background removal, inpainting prep, and isolating a subject before further generation steps. When text alone is too coarse, an interactive points editor adapted from KJNodes lets you click on the image to refine the result. It installs as a custom node through ComfyUI Manager or a manual clone, so it behaves like a normal part of your existing ComfyUI setup rather than a separate tool to learn.
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)