SHAPE-IT: Exploring Text-to-Shape-Display for Generative Shape-Changing Behaviors with LLMs

TL;DR

Text-to-shape-display is introduced, a novel approach to generating dynamic shape changes in pin-based shape displays through natural language commands using large language models and AI-chaining to facilitate rapid ideation of a wide range of shape-changing behaviors with AI.

Abstract

This paper introduces text-to-shape-display, a novel approach to generating dynamic shape changes in pin-based shape displays through natural language commands. By leveraging large language models (LLMs) and AI-chaining, our approach allows users to author shape-changing behaviors on demand through text prompts without programming. We describe the foundational aspects necessary for such a system, including the identification of key generative elements (primitive, animation, and interaction) and design requirements to enhance user interaction, based on formative exploration and iterative design processes. Based on these insights, we develop SHAPE-IT, an LLM-based authoring tool for a 24 x 24 shape display, which translates the user's textual command into executable code and allows for quick exploration through a web-based control interface. We evaluate the effectiveness of SHAPE-IT in two ways: 1) performance evaluation and 2) user evaluation (N= 10). The study conclusions highlight the ability to facilitate rapid ideation of a wide range of shape-changing behaviors with AI. However, the findings also expose accuracy-related challenges and limitations, prompting further exploration into refining the framework for leveraging AI to better suit the unique requirements of shape-changing systems.

Figures (8)

• Figure 1: Primitive, Animation, and Interaction: Fundamental shapes, motion behaviors, and user-controlled triggers for text-to-shape-display approach learned from prior pin-based shape display research.
• Figure 2: Early UI prototype (A) for creating basic geometries (B), and interaction (C).
• Figure 3: SHAPE-IT UI with an example prompt; (A) The feedback message communicates the generating steps to users, indicating Primitive, an Animation, and an Interaction scripts are generated. (B) the Parameter Control Panel; (C) Loaded scripts appear as Script Card UIs, where they can be toggled on/off.
• Figure 4: SHAPE-IT System Architecture. (A) Text Input is handed to Prompt Helper, (B) Prompt Helper processes it to provide code instructions; (C) Script Generators generate the Javascript codes based on the instructions; (D) the generated codes are executed in the frontend, controlling the shape display and creating UI elements for users to adjust parameters.
• Figure 5: A.Model Runtime Comparison. B.System Success Rate Comparison