In 3D design, specifying design objectives and visualizing complex shapes through text alone proves to be a significant challenge. Although advancements in 3D GenAI have significantly enhanced part assembly and the creation of high-quality 3D designs, many systems still to dynamically generate and edit design elements based on the shape parameters. To bridge this gap, we propose GenPara, an interactive 3D design editing system that leverages text-conditional shape parameters of part-aware 3D designs and visualizes design space within the Exploration Map and Design Versioning Tree. Additionally, among the various shape parameters generated by LLM, the system extracts and provides design outcomes within the user's regions of interest based on Bayesian inference. A user study N = 16 revealed that \textit{GenPara} enhanced the comprehension and management of designers with text-conditional shape parameters, streamlining design exploration and concretization. This improvement boosted efficiency and creativity of the 3D design process.

Various modalities have emerged in the field of 3D generative AI (GenAI) to enhance design outcomes. While some designers find inspiration in prompts to guide their design options, others prefer sketching to embody creative visions. Nonetheless, the impact of the different modalities of 3D GenAI on the design process remains largely unexplored. This study examines the utilization of prompt- and sketch-guided modalities within the design process by conducting linkography and workflow analyses with 12 designers. The results revealed that prompts played a pivotal role in stimulating initial ideation, whereas sketches played a crucial role in embodying design ideas. This investigation highlights the distinct contributions of these modalities at different phases of the design process, suggesting the potential for a more refined and synergistic collaboration between humans and AI. By elucidating the diverse functions of sketches and prompts, we propose prospective directions for the UX framework of the 3D GenAI.