# baaivision/Painter

Painter & SegGPT Series: Vision Foundation Models from BAAI

Repository: https://github.com/baaivision/Painter
Canonical: https://ross.abutalabs.com/products/baaivision-painter
Language: Python
License: MIT
License Family: permissive
Topics: cvpr2023, in-context-learning, generalist-model, generalist-painter, in-context-visual-learning, seggpt, segmentation-foundation-model
Last push: 2024-12-06T02:39:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 97
- inputs: {"age_days": 1367, "days_push": 636, "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 2593, forks 180 (observed 2026-08-28T04:07:03.009530+00:00)

## What it is
Painter and SegGPT are vision foundation models from BAAI for in-context visual learning, where a single generalist model performs diverse vision tasks specified via image prompts. SegGPT extends this to segmenting arbitrary objects in images and videos in context.

## Use cases
- segment arbitrary objects in images with a prompt
- perform in-context visual learning across vision tasks
- run generalist image-to-image vision models
- combine SAM with SegGPT for one-touch segmentation
- segment objects in videos
- research generalist vision foundation models

## When to choose
- you need a generalist segmentation model driven by visual prompts
- you want to experiment with in-context visual learning research
- you need pretrained weights for Painter or SegGPT

## When to avoid
- you need a production-ready segmentation service with an API
- you need task-specific fine-tuned models with best benchmark accuracy
- you need non-PyTorch or CPU-only inference

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, artificial-intelligence, image-processing
- platform: python
- tags: vision-foundation-models, in-context-learning, segmentation, research-code, seggpt, cvpr2023, linux, gpu

## Member repositories
- baaivision/Painter (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:03.009530+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 2026-08-30T02:22:16.064003+00:00, confidence not recorded.
  - readme: https://github.com/baaivision/Painter (fetched 2026-08-28T04:07:03.009530+00:00, sha cca986cac41c)
- Data as of 2026-08-30T08:39:29.467469+00:00.