# continue-revolution/sd-webui-segment-anything

Segment Anything for Stable Diffusion WebUI

Repository: https://github.com/continue-revolution/sd-webui-segment-anything
Canonical: https://ross.abutalabs.com/products/sd-webui-segment-anything
Language: Python
License Family: other
Topics: stable-diffusion, stable-diffusion-webui, stable-diffusion-webui-plugin, segment-anything
Last push: 2024-04-30T08:24:46+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 88
- inputs: {"age_days": 1241, "days_push": 855, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3499, forks 222 (observed 2026-08-28T04:08:07.457860+00:00)

## What it is
A Stable Diffusion WebUI extension that integrates Segment Anything and GroundingDINO to generate segmentation masks from clicks or text prompts. It enhances inpainting, ControlNet semantic segmentation, image matting, and LoRA/LyCORIS training set creation.

## Use cases
- generate segmentation masks for stable diffusion inpainting
- create masks from text prompts with grounding dino
- build lora training datasets with automatic segmentation
- improve controlnet semantic segmentation
- automate image matting
- inpaint specific objects in generated images

## When to choose
- you use AUTOMATIC1111 WebUI and want precise inpainting masks
- you need text-prompt-driven object segmentation for image editing
- you want to automate mask creation for LoRA training sets

## When to avoid
- you use a different Stable Diffusion UI like ComfyUI or Forge without compatibility
- you need a standalone segmentation tool outside the WebUI
- you cannot run GPU models locally

## Facets
- artifact type: plugin
- maturity: maintenance
- function: image-processing, computer-vision, machine-learning, ui-components
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python
- tags: stable-diffusion, segment-anything, groundingdino, controlnet, inpainting, image-matting, lora-training, webui-extension, web-server, gpu

## Member repositories
- continue-revolution/sd-webui-segment-anything (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:07.457860+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 2026-08-29T18:35:49.827420+00:00, confidence not recorded.
  - readme: https://github.com/continue-revolution/sd-webui-segment-anything (fetched 2026-08-28T04:08:07.457860+00:00, sha c92dba9555ff)
- Data as of 2026-08-30T08:39:29.467469+00:00.