Recently, the Shanghai Artificial Intelligence Laboratory (Shanghai AI Lab) unveiled its first text-image mixed creation large model, dubbed "Shusheng Puyu Lingbi" (InternLM-XComposer). Puyu Lingbi is capable of engaging in fluent Chinese-English text-image dialogues, accurately comprehending image content, and has unlocked the creative ability to "generate articles with a single click" that combine text and images. Users only need to provide a topic, and Puyu Lingbi can instantly produce an article rich with both text and images. The model employs a "three-step" algorithmic process for text-image article creation, which includes generating text, planning illustrations, and intelligently selecting images. In multiple mainstream multimodal model evaluations, Puyu Lingbi's performance ranks at the forefront, especially excelling in Chinese multimodal understanding. Puyu Lingbi has been open-sourced on platforms such as GitHub, welcoming developers to try it out and innovate with new applications.