# OpenGVLab/InternGPT

InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)

Repository: https://github.com/OpenGVLab/InternGPT
Canonical: https://ross.abutalabs.com/products/interngpt
Homepage: https://igpt.opengvlab.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: chatgpt, foundation-model, gpt, gpt-4, gradio, husky, image-captioning, langchain, llm, multimodal, vqa, internimage, llama, vicuna, video-generation, sam, segment-anything, click, imagebind, draggan
Last push: 2024-08-20T12:51:03+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 86
- inputs: {"age_days": 1213, "days_push": 743, "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 3205, forks 233 (observed 2026-08-28T04:07:48.611961+00:00)

## What it is
InternGPT (iGPT) is an open-source demo platform for showcasing AI models through a pointing-language-driven visual interactive system, supporting tools like DragGAN, ChatGPT, ImageBind, and SAM. It enables multimodal chat and interactive image editing via clicking, dragging, and drawing, and includes the fine-tuned Husky vision-language model.

## Use cases
- run a multimodal chatbot demo with image and video understanding
- interactively edit images by clicking and dragging with DragGAN
- segment objects in images using SAM through a chat interface
- host a self-hosted demo platform to showcase my AI models
- try a GPT-4-like multimodal chat with vision capabilities
- combine ImageBind with an LLM for cross-modal interaction
- demo visual question answering on images and videos

## When to choose
- you want a web demo platform to showcase vision and LLM models interactively
- you need pointing/dragging-based image editing and segmentation in a chat UI
- you want to self-host a multimodal assistant on your own GPU

## When to avoid
- you need a production-grade chatbot service rather than a research demo
- you lack a GPU, since the tools require significant GPU memory
- you only need a plain text-only LLM chat interface

## Facets
- artifact type: application
- maturity: active
- function: chatbot, agent-framework, image-processing, llm-inference, machine-learning, gui
- domain: artificial-intelligence, computer-vision, large-language-models, image-processing, chatbots
- platform: python, self-hosted
- tags: multimodal-chat, pointing-instructions, visual-interaction, draggan, segment-anything, imagebind, gradio-demo, vision-language-model, image-editing, video-generation, multimodal, web-server, gpu, docker

## Member repositories
- OpenGVLab/InternGPT (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:48.611961+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 2026-08-29T18:44:58.193409+00:00, confidence not recorded.
  - readme: https://github.com/OpenGVLab/InternGPT (fetched 2026-08-28T04:07:48.611961+00:00, sha ccff22328779)
- Data as of 2026-08-30T08:39:29.467469+00:00.