Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts. However, ambiguities inherent in natural language and out-of-distribution effects make it hard to synthesize image styles, that leverage a specific design pattern, texture or material. In this paper, we introduce StyleDrop, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. The proposed method is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. It efficiently learns a new style by fine-tuning very few trainable parameters (less than $1\%$ of total model parameters) and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a single image that specifies the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop implemented on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion. More results are available at our project website: https://styledrop.github.io

翻译：预训练的大规模文本到图像模型通过恰当使用文本提示能合成令人印象深刻的图像。然而，自然语言固有的歧义性和分布外效应使得难以合成利用特定设计模式、纹理或材质的图像风格。本文提出StyleDrop方法，该方法利用文本到图像模型实现忠实遵循特定风格的图像合成。所提方法极具通用性，可捕捉用户提供风格的细微差别与细节，例如配色方案、阴影、设计模式以及局部与全局效果。该方法通过微调极少量可训练参数（不足总模型参数的1%）高效学习新风格，并通过迭代训练（结合人工或自动化反馈）提升质量。更优的是，即使用户仅提供一张指定风格图像，StyleDrop也能生成令人印象深刻的结果。广泛研究表明，在文本到图像模型的风格调优任务中，基于Muse实现的StyleDrop显著优于其他方法（包括基于Imagen或Stable Diffusion的DreamBooth和textual inversion）。更多结果请访问项目网站：https://styledrop.github.io