【摘要】 人工智能领域的快速发展给服装设计带来了新的机遇与挑战。为了给服装设计从业者和研究人员提供新设计思路和研究方法，梳理了人工智能生成内容领域的最新研究成果，对其优化历程、应用领域进行剖析，并探讨神经对抗网络、Transformer、扩散模型、神经辐射场4类图像生成模型的优劣势。研究表明：扩散模型是服装设计领域优势较为突出的图像生成模型。基于稳态扩散模型并结合开源社区工具包进行大型预训练扩散模型的搭建，其模型及算法能够根据研究者的创作思路高效生成系列服装设计方案；该模型生成的服装设计方案可通过模糊综合评价，验证其实际效果及潜在的应用价值。该研究能够为人工智能背景下服装设计体系提供理论基础，并进一步对未来人工智能生成内容在服装设计领域的应用提供实践基础。更多还原

【Abstract】 The rapid development of artificial intelligence has brought new opportunities and challenges to the field of fashion design. To provide novel design ideas and research methods for fashion design practitioners and researchers, this study reviewed the latest research progress in the field of artificial intelligence-generated content(AIGC), analyzed its optimization process and application domains, and examined the strengths and weaknesses of four types of image generation models: Generative Adversarial Networks(GANs), Transformers, Diffusion Models, and Neural Radiance Fields(NeRF). The results demonstrate that diffusion models exhibit relatively outstanding advantages as image generation models in the context of fashion design. Based on the Stable Diffusion model and incorporating open-source community toolkits, a large-scale pre-trained diffusion model was constructed. The model and its associated algorithms can efficiently generate a series of fashion design schemes aligned with the creative intent of researchers. The design solutions produced by the model were subjected to a fuzzy comprehensive evaluation, which verified their practical effectiveness and potential application value. This research provides a theoretical foundation for fashion design systems in the context of artificial intelligence and further offers a practical basis for the future application of AIGC in the field of fashion design.更多还原