Text-to-Image synthesis is the task of generating an image according to a specific text description. Generative Adversarial Networks have been considered the standard method for image synthesis virtually since their introduction. Denoising Diffusion Probabilistic Models are recently setting a new baseline, with remarkable results in Text-to-Image synthesis, among other fields. Aside its usefulness per se, it can also be particularly relevant as a tool for data augmentation to aid training models for other document image processing tasks. In this work, we present a latent diffusion-based method for styled text-to-text-content-image generation on word-level. Our proposed method is able to generate realistic word image samples from different writer styles, by using class index styles and text content prompts without the need of adversarial training, writer recognition, or text recognition. We gauge system performance with the Fr\'echet Inception Distance, writer recognition accuracy, and writer retrieval. We show that the proposed model produces samples that are aesthetically pleasing, help boosting text recognition performance, and get similar writer retrieval score as real data. Code is available at: https://github.com/koninik/WordStylist.

翻译：文本到图像合成是指根据特定文本描述生成图像的任务。自生成对抗网络问世以来，它一直被视作图像合成的标准方法。近年来，去噪扩散概率模型在包括文本到图像合成在内的多个领域取得了显著成果，正逐步确立新的基准。除了其自身用途外，该方法在数据增强方面也尤为重要，可用于辅助训练其他文档图像处理任务的模型。在本研究中，我们提出了一种基于潜在扩散的方法，用于生成风格化的逐词文本内容图像。所提方法能够通过类别索引风格和文本内容提示，生成不同书写风格的逼真单词图像样本，且无需对抗训练、书写者识别或文本识别。我们使用弗雷歇初始距离、书写者识别准确率和书写者检索来评估系统性能。实验表明，该模型生成的样本在视觉上美观，有助于提升文本识别性能，并获得了与真实数据相似的书写者检索分数。代码地址：https://github.com/koninik/WordStylist。