Next Article in Journal
Investigating the Roadmap to Promote Building Professionals’ Internet-Based Multi-Stakeholder Collaborative Management Technology Implementation: The Moderator Roles of Organizational Institutions
Previous Article in Journal
Evaluating All-Age-Friendly Community Environments with Cross-Generational Interaction Potential: A Multi-Objective Assessment Based on Cases from China and Italy
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

AI for Garden Design Visualization: Development and Validation of the GardenDiff Model

1
School of Landscape Architecture, Zhejiang Agricultural & Forestry University, Hangzhou 311300, China
2
School of Engineering and Design, Technical University of Munich, 80333 Munich, Germany
*
Authors to whom correspondence should be addressed.
Buildings 2026, 16(11), 2195; https://doi.org/10.3390/buildings16112195
Submission received: 2 April 2026 / Revised: 7 May 2026 / Accepted: 26 May 2026 / Published: 29 May 2026
(This article belongs to the Section Architectural Design, Urban Science, and Real Estate)

Abstract

The rapid advancement of AI-driven generative design brings new opportunities, but its application in landscape garden design remains limited by two gaps: (1) semantic misalignment between generated images and the designer’s intent, and (2) low-resolution outputs with insufficient details. To address these gaps, we developed GardenDiff, a domain-adapted diffusion model trained via parameter optimization and a specialized landscape garden dataset. Central to this approach is Structured Design Captioning (SDC), a hierarchical annotation system specifically designed for garden design that encodes design elements, style features, and auxiliary scene information. To develop this model, we designed a three-stage experimental framework. In Stage 1, we examined the effects of training caption systems and training resolution on generated landscape garden imagery by controlled experiments. In Stage 2, we conducted joint training across five garden styles (Chinese, Japanese, Mediterranean, Nordic, and English) based on the optimized parameter settings from Stage 1 to construct the GardenDiff model. In Stage 3, we validated the model performance through expert evaluation (N = 36) and public evaluation (N = 136) and analyzed style-specific variations in the generated outcomes. Research results showed that Structured Design Captioning (SDC) improved Spatial Rationale by 19.67–39.46% compared with generic captions, and training at 1536 × 1536 pixels improved image quality by 23.2% compared with 768 × 768-pixel training. GardenDiff trained with these optimized parameters showed notable advantages. Its overall scores (5.06) exceeded those of Stable Diffusion XL base 1.0 (SDXL 1.0) by 16.4% and DreamShaper XL by 22.4%. The model improved across four dimensions, including Design Rationale, Design Professionalism, Design Accuracy, and Design Satisfaction. Our study offers a new model to improve the perspective visualization of generative garden design and provides insights into AI-informed landscape and urban design.
Keywords: landscape garden design; LoRA fine-tuning; structured design captioning; generative design; artificial intelligence landscape garden design; LoRA fine-tuning; structured design captioning; generative design; artificial intelligence

Share and Cite

MDPI and ACS Style

Sun, X.; Chen, X.; Zhou, C.; Wu, S.; Zhao, H.; Li, K. AI for Garden Design Visualization: Development and Validation of the GardenDiff Model. Buildings 2026, 16, 2195. https://doi.org/10.3390/buildings16112195

AMA Style

Sun X, Chen X, Zhou C, Wu S, Zhao H, Li K. AI for Garden Design Visualization: Development and Validation of the GardenDiff Model. Buildings. 2026; 16(11):2195. https://doi.org/10.3390/buildings16112195

Chicago/Turabian Style

Sun, Xiaolong, Xi Chen, Chao Zhou, Shengsha Wu, Hongbo Zhao, and Kun Li. 2026. "AI for Garden Design Visualization: Development and Validation of the GardenDiff Model" Buildings 16, no. 11: 2195. https://doi.org/10.3390/buildings16112195

APA Style

Sun, X., Chen, X., Zhou, C., Wu, S., Zhao, H., & Li, K. (2026). AI for Garden Design Visualization: Development and Validation of the GardenDiff Model. Buildings, 16(11), 2195. https://doi.org/10.3390/buildings16112195

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop