PozzettiAndrea/ComfyUI-SAM3

ComfyUI wrapper for segment anything 3

What it solves

This project provides a ComfyUI integration for Meta's SAM3 (Segment Anything Model 3), enabling users to perform open-vocabulary image and video segmentation using natural language text prompts.

How it works

It integrates the SAM3 model into the ComfyUI node-based interface, allowing users to define segments of images or videos via text prompts or by using an interactive points editor to specify target areas.

Who it’s for

Users of ComfyUI who want to integrate advanced image and video segmentation capabilities into their generative AI workflows.

Highlights

  • Open-vocabulary segmentation: Segment objects based on natural language descriptions.
  • Image and video support: Works across both static images and moving pictures.
  • Interactive points editor: Includes a simplified points editor for precise, point-based segmentation.

Related

  • Project
    facebookresearch/sam3

    SAM 3 (Segment Anything with Concepts) is Meta’s 848 M‑parameter foundation model that lets you prompt an image or video with free‑form text (or visual exemplars) and receive masks, boxes, and scores for *all* matching objects. It combines a DETR‑style detector and a SAM 2‑style tracker, introduces a presence token for fine‑grained prompt discrimination, and is trained on >4 M auto‑annotated concepts. The repo provides installation steps, example notebooks, and a new SA‑CO benchmark (270 K concepts) for evaluation.

  • Project
    nkxx188/ComfyUI-MiniMaxH3-Easy

    A compact ComfyUI interface for MiniMax H3 that simplifies text-to-video, image-to-video, and reference-based video generation with a unified media input system.

  • Project
    PozzettiAndrea/ComfyUI-SAM3DBody

    A ComfyUI wrapper for Meta's SAM 3D Body that enables full-body 3D human mesh recovery from a single image.

  • Project
    yatengLG/ISAT_with_segment_anything

    An interactive semi-automatic image segmentation annotation tool that uses the Segment Anything Model (SAM) to accelerate the creation of labeled datasets.

  • Project
    gokayfem/ComfyUI_VLM_nodes

    A production-oriented suite of ComfyUI nodes for vision-language models, providing structured detection, segmentation, and adaptive video reasoning with VRAM optimizations.