Landscape renderings are realistic images of landscape sites, allowing stakeholders to perceive better and evaluate design ideas. While recent advances in Generative Artificial Intelligence (GAI (generative artificial intelligence)) enable automated generation of landscape renderings, the End to End (endtoend) methods are not compatible with common design processes, leading to insufficient alignment with design idealizations and limited cohesion of iterative landscape design. Informed by a formative study for comprehending design requirements, we present PlantoGraphy, an iterative design system that allows for interactive configuration of generative artificial intelligence models to accommodate human-centered design practice. A two-stage pipeline is incorporated: first, the concretization module transforms conceptual ideas into concrete scene layouts with a domain-oriented large language model; and second, the illustration module converts scene layouts into realistic landscape renderings with a layout-guided diffusion model Fine-tune (finetune)ed through Low-Rank Adaptation (LoRA) (lora). PlantoGraphy has undergone a series of performance evaluations and user studies, demonstrating its effectiveness in landscape rendering generation and the high recognition of its interactive functionality.
This paper presents a novel modeling method and a series of artworks that transform 2D Chinese calligraphy into 3D forms, offering a new perspective for understanding and appreciating traditional Chinese calligraphy beyond its conventional 2D representation. Drawing inspiration from the multidimensional nature of the calligraphic formation process and the philosophies of ancient calligraphers regarding the intrinsic depth of calligraphy, we propose a 3D modeling approach of Chinese calligraphy. This method analyzes stroke structures, incorporates volume modeling, and applies parametric optimization to a given 2D calligraphic script. The proposed technique seeks to preserve the original aesthetic essence by capturing the natural flow, spatial depth, structural dynamics, and layering of the calligraphy, while extending its expression into the 3D realm. A series of artworks created through this process have been exhibited, with feedback from both the public and experienced calligraphers indicating the unique value of appreciating traditional calligraphy beyond the original scripts.
Chinese calligraphy, a cherished aspect of Chinese and global culture, employs Chinese characters as its medium, while ink and brush serve as instrumental tools, resulting in a distinctive aesthetic allure. Calligraphy comprises intricate imagery that not only captures the abstract forms of characters but also conveys the essence of natural landscapes, thereby stimulating viewers’ imagination. This research aims to explore a methodology for materializing calligraphic imagery, by utilizing AI generative models to produce corresponding images based on the form, meaning, and contextual aspects of calligraphy. The generated result present an artistic style that seamlessly integrates Chinese calligraphy and Chinese painting. Further, the comparison between different style of generated result shows that Chinese painting has stronger generalization ability.