# OpenGVLab/VisionLLM

VisionLLM Series

Repository: https://github.com/OpenGVLab/VisionLLM
Canonical: https://ross.abutalabs.com/products/visionllm
Homepage: https://arxiv.org/abs/2305.11175
Language: Python
License: Apache-2.0
License Family: permissive
Topics: large-language-models, object-detection, generalist-model
Last push: 2025-02-27T08:31:04+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 8, release rhythm 35, longevity 85
- inputs: {"age_days": 1203, "days_push": 552, "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 1153, forks 63 (observed 2026-08-28T04:03:47.282284+00:00)

## What it is
VisionLLM is a series of open-source multimodal large language models from OpenGVLab that unify vision-centric tasks under language instructions. VisionLLM v2 is a generalist model supporting hundreds of vision-language tasks spanning visual understanding, perception, and generation.

## Use cases
- run a multimodal LLM for image understanding and captioning
- perform open-ended object detection with language instructions
- generate images from a vision-language model
- research unified vision and language task frameworks
- evaluate a generalist model across hundreds of vision-language tasks
- build instruction-driven visual perception pipelines

## When to choose
- you need a single generalist model covering visual understanding, perception, and generation
- you want open-ended, instruction-driven object detection or vision tasks
- you are reproducing or extending the VisionLLM NeurIPS papers

## When to avoid
- you need a lightweight production vision API rather than research code
- you lack GPU resources for large multimodal models
- you need a narrowly specialized detection model with minimal overhead

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, llm-inference, image-processing
- domain: computer-vision, large-language-models, artificial-intelligence, deep-learning
- platform: python
- tags: multimodal, vision-language-model, object-detection, generalist-model, research-code, image-generation, gpu, linux

## Member repositories
- OpenGVLab/VisionLLM (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:47.282284+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 2026-08-30T06:33:26.125282+00:00, confidence not recorded.
  - readme: https://github.com/OpenGVLab/VisionLLM (fetched 2026-08-28T04:03:47.282284+00:00, sha 4d791b62259f)
  - homepage: https://arxiv.org/abs/2305.11175 (fetched 2026-08-29T12:37:58.214640+00:00, sha 791013c49aad)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:37:58.223905+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:37:58.227389+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:37:58.229534+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:37:58.225681+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.