# storyicon/comfyui_segment_anything

Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.

Repository: https://github.com/storyicon/comfyui_segment_anything
Canonical: https://ross.abutalabs.com/products/comfyui_segment_anything
Language: Python
License: Apache-2.0
License Family: permissive
Topics: comfyui, groundingdino, sam, segment-anything, custom-nodes, stable-diffusion
Last push: 2024-07-12T10:17:33+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 75
- inputs: {"age_days": 1061, "days_push": 782, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1113, forks 110 (observed 2026-08-28T04:03:38.085563+00:00)

## What it is
A ComfyUI custom node that combines GroundingDINO and Segment Anything (SAM) to segment any element in an image using semantic text prompts. It is a port of sd-webui-segment-anything, providing consistent outputs with the original extension.

## Use cases
- segment objects in an image using text descriptions
- create masks for inpainting in stable diffusion workflows
- isolate a subject from its background in ComfyUI
- text-prompted image segmentation with SAM and GroundingDINO
- extract specific elements from images for editing
- build automated masking pipelines in ComfyUI

## When to choose
- you use ComfyUI and need text-guided segmentation or masking
- you want SAM-based segmentation driven by semantic prompts
- you need inpainting masks generated automatically from descriptions
- you want parity with sd-webui-segment-anything inside ComfyUI

## When to avoid
- you need a standalone segmentation tool outside ComfyUI
- you lack a GPU or disk space for multi-gigabyte SAM and GroundingDINO models
- you need features beyond the core segmentation functionality, which is still partially implemented

## Facets
- artifact type: plugin
- maturity: active
- function: image-processing, computer-vision, machine-learning, plugin-system
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python, cross-platform
- tags: comfyui, comfyui-custom-nodes, segment-anything, groundingdino, stable-diffusion, image-segmentation, text-prompted-segmentation, gpu

## Member repositories
- storyicon/comfyui_segment_anything (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.085563+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:42:37.953837+00:00, confidence not recorded.
  - readme: https://github.com/storyicon/comfyui_segment_anything (fetched 2026-08-28T04:03:38.085563+00:00, sha 89f4b66a4e1b)
- Data as of 2026-08-30T08:39:29.467469+00:00.