InternLM/InternLM-XComposer

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2925 stars · 174 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

InternLM-XComposer is a family of large vision-language models from the InternLM team, including XComposer2.5 for long-context multimodal understanding, an OmniLive system for streaming video/audio interaction, and a multimodal reward model. It ships model weights, training code, and evaluation scripts for multimodal comprehension and text-image composition.

Use cases

• run a vision-language model for image and video understanding
• build a multimodal chatbot that processes streaming video and audio
• fine-tune a large vision-language model with supervised finetuning
• score multimodal model outputs with a reward model
• understand long-context video and high-resolution images with an LLM

When to choose

• you need an open Apache-2.0 vision-language model with weights and training code
• you want streaming real-time video and audio interaction in one system
• you need long-context or 4K-resolution image understanding

When to avoid

• you only need text-only LLM inference
• you lack GPU resources for 7B-scale multimodal models
• you need a production-ready managed multimodal API rather than self-hosted models

Facets

library · maturity active

machine-learning deep-learning llm-inference chatbot nlp image-processing audio-processing video-processing large-language-models machine-learning computer-vision artificial-intelligence python cross-platform vision-language-model multimodal streaming-video streaming-audio reward-model instruction-tuning foundation-model internlm natural-language-processing audio video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="InternLM/InternLM-XComposer")