Architectural designing relies on the professional skills and concepts of designers. Outstanding architectural designs play a crucial role in showcasing the image of a city [ 2 , 3 , 4 ]. Moreover, iconic landmark architecture in a city stimulates local employment and boosts the tourism industry [ 1 , 25 ].

Designers typically communicate architectural design proposals with clients through visual renderings. However, this conventional method has low efficiency and low quality. The inefficiency stems from the complexity of the conventional design process involving extensive manual drawing tasks [2,5 5], such as creating 2D drawings, building 3D models, applying material textures, and rendering visual effects [ 26 ]. This linear design process restricts client involvement in the decision-making until producing the final rendered images. If clients find the design not to meet their expectations upon viewing the final images, designers must redo the entire design, leading to repetitive modifications [ 2 , 3 , 4]. Consequently, the efficiency of this design practice needs improvement [ 26 ].

建筑设计质量低下的原因在于优秀设计师培养难度大、设计能力提升过程漫长。设计者缺乏设计技能导致设计质量难以提高The reason for the low quality of architectural design is that it is difficult to train excellent designers and the process of improving design capabilities is long. Designers' lack of design skills makes it difficult to improve design quality [ 4,5,6 ]。然而，设计能力的提升是一个渐进的过程，设计师必须不断学习新的设计方法，探索不同的设计风格 . However, the improvement of design capabilities is a gradual process , and designers must constantly learn new design methods and explore different design styles [ 2,3,6,27,28,29 ] . At the same time, 。同时，在复杂条件下寻求最佳设计方案也给设计者带来了巨大的挑战seeking the best design solution under complex conditions also brings huge challenges to designers [ 2 , 5 ]。.

所有这些因素最终导致低效和低质量的架构设计All these factors ultimately lead to inefficient and low-quality architectural designs [ 2 , 5 ]。因此，必须及时将新技术引入建筑行业来解决这些问题。. Therefore, new technologies must be introduced into the construction industry in a timely manner to solve these problems.

近年来，扩散模型迅速发展成为主流的图像生成模型In recent years, the diffusion model has rapidly developed into a mainstream image generation model [ 19, 20,21,22,30, 21 , 22, 30, 31 ] ，可以使设计者快速获取图像，从而显着提高建筑设计效率和质量, which allows designers to quickly obtain images, thereby significantly improving the efficiency and quality of architectural design [ 13 , 32 ]。.

传统的扩散模型包括前向过程和后向过程。在前向过程中，噪声不断地添加到输入图像中，将其转变为噪声图像。后向过程的目的是从噪声图像中恢复原始图像The traditional diffusion model includes forward process and backward process. During the forward process, noise is continuously added to the input image, transforming it into a noisy image. The purpose of the backward process is to restore the original image from the noisy image [ 33 ]。通过学习图像去噪过程，扩散模型获得了生成图像的能力. By learning the image denoising process, the diffusion model acquires the ability to generate images [ 32 , 34 ]。当需要生成具有特定设计元素的图像时，设计者可以将文本提示纳入扩散模型的去噪过程中，以生成一致的图像并实现对生成结果的可控性[. When there is a need to generate images with specific design elements, designers can incorporate text cues into the denoising process of the diffusion model to generate consistent images and achieve controllability over the generated results [ 35 , 35、36、6, 37、38、39 , 38, 39 ]，, 40 ]。使用文本引导扩散模型进行图像生成的优点在于它们可以简单地控制图像的生成. The advantage of using text-guided diffusion models for image generation is that they allow simple control of image generation [ 12, 14,41,42, 41, 42 , 43 ]。 .

尽管扩散模型在大多数领域都表现出色，但它们在建筑设计中的应用仍然有改进的空间Although diffusion models perform well in most fields, there is still room for improvement in their application in architectural design [ 35 , 44 ]。具体来说，限制来自于获取大量互联网数据进行训练，而这些数据缺乏具有专业架构术语的高质量注释。结果，该模型在学习过程中无法在建筑设计和建筑语言之间建立联系，这使得使用专业设计词汇对建筑设计生成进行指导变得具有挑战性. Specifically, the limitation comes from obtaining large amounts of Internet data for training, which lacks high-quality annotations with professional architectural terminology. As a result, the model fails to establish connections between architectural design and architectural language during the learning process, which makes it challenging to use professional design vocabulary to guide architectural design generation [ 45, 46,47, 47, 48]。因此，有必要收集高质量的建筑设计图像，用相关信息对其进行注释，然后对模型进行微调以使其适应建筑设计任务。 ] . Therefore, it is necessary to collect high-quality architectural design images, annotate them with relevant information, and then fine-tune the model to adapt it to the architectural design task.

扩散模型通过针对新场景的整个再训练或微调来学习新的知识和概念。由于整个模型重新训练的成本巨大，需要大量图像数据集，并且训练时间较长Diffusion models learn new knowledge and concepts through complete retraining or fine-tuning for new scenarios. Due to the huge cost of retraining the entire model, the need for large image datasets, and the long training time [ 11 , 15 ]，模型微调是目前最可行的。, model fine-tuning is currently the most feasible.

有四种标准微调方法。第一个是文本反转There are four standard methods of fine-tuning. The first is text inversion [ 11, 36, 46,49 , 49]，即冻结文本到图像模型，仅提供最合适的嵌入向量来嵌入新知识。该方法提供了快速的模型训练和最少的生成模型，但图像生成效果普通。第二种是, which freezes the text-to-image model and provides only the most suitable embedding vectors to embed new knowledge . This method provides fast model training and minimal generative models, but the image generation effect is mediocre. The second is the Hypernetwork [ 47 ]方法，即在原始扩散模型的中间层插入一个单独的小神经网络来影响输出。该方法训练速度较快，但图像生成效果一般。第三个是 method, which inserts a separate small neural network in the middle layer of the original diffusion model to affect the output. This method is faster to train, but the image generation effect is average. The third one is LoRA [ 48 ]，即为跨层注意力分配权重，以允许学习新知识。该方法在中等训练时间后可以生成平均数百MB大小的模型，且图像生成效果较好。第四种是, which assigns weights to cross-layer attention to allow learning new knowledge. This method can generate models with an average size of hundreds of MB after moderate training time, and the image generation effect is good. The fourth is the Dreambooth[ 45 ]方法，即对原始扩散模型进行整体微调。使用该方法，设计了先验保留损失来训练扩散模型，使其能够生成符合提示的图像，同时防止过度拟合 method, which is an overall fine-tuning of the original diffusion model. Using this method, a prior-preserving loss was designed to train the diffusion model, enabling it to generate images consistent with the cues while preventing overfitting [ 50 , 51 ]。命名新知识时建议使用稀有词汇，以避免由于与原始模型词汇相似而导致语言漂移. It is recommended to use rare vocabulary when naming new knowledge to avoid language drift due to similarity with the original model vocabulary [ 50 , 51 ]。该方法只需要特定主题的 3 到 5 个图像以及相应的文本描述，即可针对特定情况进行微调，并将特定文本描述与输入图像的特征相匹配。微调模型根据特定主题词和一般描述符生成图像. This method requires only 3 to 5 images of a specific subject and corresponding text descriptions, can be fine-tuned for specific situations, and matches specific text descriptions to the characteristics of the input images. Fine-tuned models generate images based on specific topic terms and general descriptors [ 31 , 46]. Since the entire ]。由于整个模型是使用model is fine-tuned using the Dreambooth 方法进行微调的，因此产生的结果通常是这些方法中最好的。method, the results produced are usually the best of these methods.