# UX-Decoder/Segment-Everything-Everywhere-All-At-Once

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Repository: https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once
Canonical: https://ross.abutalabs.com/products/segment-everything-everywhere-all-at-once
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-08-19T08:01:54+00:00

## Health v2 (maintenance only)
Score: 20/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 88
- inputs: {"age_days": 1239, "days_push": 744, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4794, forks 449 (observed 2026-08-28T04:09:00.003021+00:00)

## What it is
SEEM is the official PyTorch implementation of the NeurIPS 2023 paper 'Segment Everything Everywhere All at Once', a model for universal image segmentation driven by multi-modal prompts. It supports visual prompts (points, boxes, scribbles, image segments) and language prompts (text, audio), individually or in combination.

## Use cases
- segment objects in an image using text prompts
- click or scribble on an image to segment a region
- segment everything in an image automatically
- combine point and text prompts for interactive segmentation
- use segmentation as visual prompting for GPT-4V
- integrate segmentation into multimodal chat demos

## When to choose
- you need state-of-the-art interactive or promptable image segmentation
- you want multi-modal prompting (text, points, boxes, scribbles, audio) in one model
- you are doing research on universal segmentation or visual prompting

## When to avoid
- you need a lightweight production segmentation service with minimal dependencies
- you only need simple classical segmentation like thresholding or edge detection
- you lack a GPU or cannot build CUDA-based vision dependencies

## Facets
- artifact type: library
- maturity: stable
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence, deep-learning
- platform: python
- tags: image-segmentation, multimodal-prompts, interactive-segmentation, research-code, neurips-2023, linux, gpu

## Member repositories
- UX-Decoder/Segment-Everything-Everywhere-All-At-Once (main) score 20

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:00.003021+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 2026-08-29T18:18:40.400964+00:00, confidence not recorded.
  - readme: https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once (fetched 2026-08-28T04:09:00.003021+00:00, sha d95bc7e939ef)
- Data as of 2026-08-30T08:39:29.467469+00:00.