Artificial Intelligence (AI) has shown immense potential in various fields, and its utilization in landscape architecture is still in the early stages of exploration and refinement. An automated floral landscape design model has been developed by harnessing computer vision and machine learning, paving the way for AI applications in floral landscape design. As a case study, the North Long Lake Wetland Park floral exhibition from the first Henan Province Floral Landscape Competition was used as a reference material repository. An extensive collection of floral landscape photographs was gathered as training data for the model. Computer vision algorithms were employed to analyze and extract features from real-world floral landscape images. A machine learning model was trained to generate new floral landscape design concepts based on semantic segmentation maps and input keywords. This machine learning model can produce high-quality and diverse design proposals for various types of floral landscapes, while also identifying and extracting characteristics of floral plants, such as species, scale, and spatial relationships. Furthermore, the effectiveness of AI-generated floral layout proposals was evaluated to validate the feasibility and applicability of AI technology in floral landscape design. This research aims to provide innovative perspectives and insights for the theoretical research and practical application of AI technology in the field of plant landscape design.