Shap-Explorer: Introducing Manipulable Text-to-3D Generation Into 3D Art Creation

 Generative Artificial Intelligence (GAI) technologies are increasingly employed by artists for their capability to rapidly generate intricate designs. While text-to-image (T2I) applications have been explored in art creation with constructive outcomes, the integration of text-to-3D (T23D) methodologies remains underexplored, primarily due to the knowledge gap between users and tool-makers. Developers aim to refine models for speed and accuracy, yet artists lack a steerable front-end tool to guide the 3D generation. 

To bridge this gap, this research introduces Shap-Explorer, a tool that streamlines the use of T23D, enabling users to iteratively modify the output models through mesh generator and control the generation through process controller and text deformer. Through a preliminary user study, this research examines the affordance of T23D and the impact of enhanced interactions on the generative system, such as providing design alternatives. 

Insights include, for example, how users can iteratively refine and adjust the generated 3D models to align with their creative vision into the manipulation capabilities of generative AI tools in the design workflow, offering a step forward in the interactive creation of 3D art.