WeDesign: Generative AI-Facilitated Community Consultations for Urban Public Space Design

2025-08-13

AI Summary

Public consultation in urban planning often lacks inclusivity due to resource constraints, sensory impairments, and power asymmetries. This paper proposes a generative AI–enhanced participatory design framework, integrating Stable Diffusion XL into a custom-built platform, WeDesign, which supports real-time text-to-image generation, multilingual interaction, interactive image editing, and collaborative voting. The framework significantly strengthens design expressivity and deliberative agency for marginalized groups—including persons with disabilities, older adults, and non-native speakers. Validated through multiple field workshops and in-depth interviews, the platform effectively stimulates diverse ideation, deepens engagement, and improves collaborative equity; however, challenges persist in visualizing the needs of marginalized communities. The study advocates for an open-source, extensible collaborative infrastructure to advance the sustainable deployment of generative AI in inclusive urban governance.

Technology Category

• Humans and AI: AI for Accessibility
• Planning, Routing, and Scheduling: Planning with Language Models
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Community consultations are integral to urban planning processes intended to incorporate diverse stakeholder perspectives. However, limited resources, visual and spoken language barriers, and uneven power dynamics frequently constrain inclusive decision-making. This paper examines how generative text-to-image methods, specifically Stable Diffusion XL integrated into a custom platform (WeDesign), may support equitable consultations. A half-day workshop in Montreal involved five focus groups, each consisting of architects, urban designers, AI specialists, and residents from varied demographic groups. Additional data was gathered through semi-structured interviews with six urban planning professionals. Participants indicated that immediate visual outputs facilitated creativity and dialogue, yet noted issues in visualizing specific needs of marginalized groups, such as participants with reduced mobility, accurately depicting local architectural elements, and accommodating bilingual prompts. Participants recommended the development of an open-source platform incorporating in-painting tools, multilingual support, image voting functionalities, and preference indicators. The results indicate that generative AI can broaden participation and enable iterative interactions but requires structured facilitation approaches. The findings contribute to discussions on generative AI's role and limitations in participatory urban design.

Problem

• Addresses inclusive decision-making barriers in urban planning consultations
• Explores generative AI for visualizing diverse stakeholder design needs
• Examines limitations in representing marginalized groups and local architecture

Innovation

• Uses Stable Diffusion XL for visual generation
• Integrates custom platform with in-painting tools
• Supports multilingual prompts and voting functionalities