A Cross-Stage Human-GenAI Collaborative Workflow for Landscape Architecture Design: A Pocket Park Feasibility Study
Open Access
- 25 September 2026
- Vol. 16 (19) , 3819
Abstract
Research on generative artificial intelligence (GenAI) in landscape architecture has largely focused on individual design stages. Few studies have examined how selected design information can transfer across design stages and how landscape architecture expertise can be incorporated into a workflow-level process. This study proposes a human–GenAI collaborative workflow that integrates design knowledge at each stage and facilitates information transfer across 2D plan generation, 3D spatial construction, and scene rendering. The workflow is implemented with a Stable Diffusion (v1.5) model fine-tuned with LoRA and conditioned by ControlNet, and comprises three stages. First, professional knowledge is encoded as semantic constraints, and the designer validates the results. Next, the designer translates the selected 2D plan into a 3D spatial model through designer-led spatial interpretation and modeling. Finally, the designer combines multi-condition rendering with professional knowledge and selects the final alternative. A pocket park case study demonstrates the feasibility of the proposed workflow. The generated alternatives were assessed against the stated design criteria in this case, and the results show the designer’s decisions at each stage and how those decisions informed the subsequent stage.Keywords
Funding Information
- National Natural Science Foundation of China (52308064)
- 2025 Nanjing Tech University Institutional Teaching Reform Project (177)
- Philosophy and Social Science Research Project of Jiangsu Higher Education Institutions (2025SJYB0167)
- 2026 Postgraduate Research & Practice Innovation Program of Jiangsu Province (PX-1226146)
This publication has 52 references indexed in Scilit:
- DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation Using Limited DataInternational Journal of Computer Vision, 2025
- Generative AI models for different steps in architectural design: A literature reviewFrontiers of Architectural Research, 2025
- Research note: assessing human preferences for natural landscapes—an analysis of ChatGPT-4 and LLaVA modelsLandscape and Urban Planning, 2025
- AI-generated content in landscape architecture: A surveyAI Open, 2025
- Implicit Style-Content Separation Using B-LoRA2024
- Semantic floorplan segmentation using self-constructing graph networksAutomation in Construction, 2024
- Vitruvio: Conditional variational autoencoder to generate building meshes via single perspective sketchesAutomation in Construction, 2024
- AI for conceptual architecture: Reflections on designing with text-to-text, text-to-image, and image-to-image generatorsFrontiers of Architectural Research, 2024
- The importance of designing the spatial distribution and density of vegetation in urban parks for increased experience of safetyJournal of Cleaner Production, 2023
- Group Decision Making and the AHP1989