InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition

TL;DR

InternLM-XComposer is a large vision-language model that advances text-image comprehension and composition, enabling seamless integration of images into text and achieving state-of-the-art results across multiple benchmarks.

Contribution

The paper introduces InternLM-XComposer, a novel model capable of interleaved text-image composition and multilingual understanding, with a new evaluation procedure for text-image composition quality.

Findings

Achieves state-of-the-art results on multiple vision-language benchmarks.

Effectively generates coherent articles with integrated images based on instructions.

Demonstrates competitive performance with GPT4-V and GPT3.5 in text-image composition.

Abstract

We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition. The innovative nature of our model is highlighted by three appealing properties: 1) Interleaved Text-Image Composition: InternLM-XComposer can effortlessly generate coherent and contextual articles that seamlessly integrate images, providing a more engaging and immersive reading experience. Simply provide a writing instruction, and our system will generate the corresponding manuscript. It can intelligently identify the areas in the text where images would enhance the content and automatically insert the most appropriate visual candidates. 2) Comprehension with Rich Multilingual Knowledge: The text-image comprehension is empowered by training on an extensive multi-modal multilingual database with carefully crafted strategies, resulting in a deep understanding of visual content. 3) State-of-the-art Performance: Our model consistently achieves state-of-the-art results across various mainstream benchmarks for vision-language foundational models, including MME Benchmark, MMBench, MMBench-CN, Seed-Bench, CCBench (Chinese Cultural Benchmark), QBench and Tiny LVLM. Owing to the absence of established metrics for quantitatively assessing text-image composition, we have devised a robust evaluation procedure that comprises both human and GPT4-Vision (GPT4-V) to ensure reliability. Notably, our InternLM-XComposer achieves competitive text-image composition scores compared to public solutions, including GPT4-V and GPT3.5. Collectively, InternLM-XComposer seamlessly blends advanced text-image comprehension and composition, revolutionizing vision-language interaction and offering new insights and opportunities. The InternLM-XComposer model series are publicly available at https://github.com/InternLM/InternLM-XComposer.