Rural public cultural spaces serve as vital venues for information exchange, interpersonal interaction, and cultural and leisure activities in rural communities. Since the Rural Revitalization Strategy was proposed in 2017, the planning and provision of rural public cultural spaces have attracted increasing attention in China. However, many such spaces remain underutilized, accompanied by low levels of user satisfaction among villagers. A key reason for this is the mismatch between standardized spatial configurations and villagers’ dynamic functional needs. Drawing on Hertzberger’s theory of spatial polyvalence, this study proposes a framework to evaluate spatial flexibility in rural public cultural spaces. The framework introduces quantitative indicators and computational methods across two dimensions: “competence”, referring to a space’s potential to accommodate multiple functions, and “performance”, reflecting the efficiency of functional transformation during actual use. Employing the proposed method, this study conducts a case analysis of the Xiangyang Village Neighborhood Center in Shanghai to evaluate its spatial characteristics and actual usage. The evaluation reveals two key issues at the overall level: (1) many residual spaces remain undesigned and lack strategies to support spontaneous use; (2) the spatial layout shows rigid public–private divisions, with little adaptability. At the room level, spaces such as the elevator, hairdressing room, party secretary’s office, and health center are functionally rigid and underutilized. Drawing on exemplary cases, this study proposes several key strategies such as (1) optimizing and innovatively activating residual spaces, (2) integrating multifunctional programs, and (3) improving spatial inclusiveness.

Recent advancements in artificial intelligence, particularly in generative technologies, have significantly redefined the design paradigm for community public cultural spaces, shifting from a traditionally designer-centric model to one that emphasizes multi-stakeholder co-creation. This paper focuses on the design of public cultural spaces at the community scale, proposing a generative dynamic workflow-based co-creation framework that integrates large language models (LLMs) with text-to-image technologies. The framework includes a natural dialogue-based needs-capturing module, a needs analysis module, and a needs expression text-to-image module. This study validates the proposed framework by developing a system prototype for renovating a public space in a student dormitory at Tongji University’s Jiading campus. The results show that the prototype demonstrates good usability and a relatively satisfactory capability in capturing user requirements. These findings indicate that this research helps address key limitations in traditional community design practices, such as limited resident participation, inefficient integration of diverse needs, and slow iteration processes.