# visual-openllm/visual-openllm

something like visual-chatgpt, 文心一言的开源版

Repository: https://github.com/visual-openllm/visual-openllm
Canonical: https://ross.abutalabs.com/products/visual-openllm
Language: Python
License Family: other
Last push: 2024-02-24T13:12:20+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 89
- inputs: {"age_days": 1256, "days_push": 921, "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 1186, forks 157 (observed 2026-08-28T04:03:55.180207+00:00)

## What it is
An open-source tool that interactively connects different visual models with an LLM, built on ChatGLM, Visual ChatGPT, and Stable Diffusion. It is positioned as an open-source alternative to Baidu's ERNIE Bot (文心一言) with multimodal chat and image capabilities.

## Use cases
- chat with an LLM that can also generate and edit images
- run an open-source alternative to ERNIE Bot / visual ChatGPT
- visual question answering over images
- image-to-image editing via pix2pix
- connect ChatGLM with Stable Diffusion in one interactive tool

## When to choose
- you want a self-hosted multimodal chatbot combining ChatGLM and visual tools
- you need text-to-image and image editing inside a chat interface
- you want an open-source ERNIE Bot-like experience

## When to avoid
- you need a production-grade, actively maintained project
- you require a permissive license (repository has none)
- you need support for many LLM backends or multi-turn chat out of the box

## Facets
- artifact type: application
- maturity: maintenance
- function: chatbot, llm-inference, image-processing, agent-framework, stable-diffusion
- domain: large-language-models, artificial-intelligence, computer-vision, chatbots, image-processing
- platform: python, cross-platform
- tags: visual-chatgpt, chatglm, multimodal, open-source-ernie-bot, vqa, text-to-image

## Member repositories
- visual-openllm/visual-openllm (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.180207+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 2026-08-30T06:24:05.506423+00:00, confidence not recorded.
  - readme: https://github.com/visual-openllm/visual-openllm (fetched 2026-08-28T04:03:55.180207+00:00, sha 0d0ca8196189)
- Data as of 2026-08-30T08:39:29.467469+00:00.