The paper presents GraphiMind, a tool designed to simplify the process of creating information graphics, especially for non-professionals. It emphasizes the challenges that non-experts face in creating compelling information graphics due to the need for diverse skills and comprehensive knowledge. The authors propose a solution in the form of a Large Language Model (LLM) centric interface, GraphiMind, which can automatically generate, recommend, and compose information graphics design resources based on user intent expressed through natural language. It integrates a Textual Conversational Interface, powered by tool-augmented LLM, with a traditional Graphical Manipulation Interface, streamlining the entire design process. The tool highlights the potential of LLMs in reshaping the domain of information graphics design, offering a blend of automation, versatility, and user-centric interactivity.
Publication date: 25 Jan 2024
Project Page: Not Provided
Paper: https://arxiv.org/pdf/2401.13245
