CustomText：利用扩散模型实现定制化文本图像生成
CustomText: Customized Textual Image Generation using Diffusion Models
AI总结：
针对现有扩散模型文本渲染不准、字体属性控制有限的问题，提出CustomText方法，结合预训练TextDiffuser与针对一致性解码器训练的ControlNet，实现精准文本定制，在相关数据集上表现优于现有方法。
摘要：
文本图像生成广泛应用于广告、教育、产品包装、社交媒体、信息可视化和品牌推广等多个领域。尽管近年来基于扩散模型的语言引导图像合成取得了进展，但现有模型虽擅长图像生成，却难以实现精准的文本渲染，且对字体属性的控制能力有限。本文旨在提升高质量图像的合成效果，实现精准的文本定制，从而推动图像生成模型的发展，我们将所提方法命名为CustomText。该方法依托预训练的TextDiffuser（文本扩散）模型，可实现对字体颜色、背景和字体类型的控制；此外，为解决小字号字体渲染精度不足的难题，我们为一致性解码器训练了ControlNet模型，显著提升了文本生成性能。我们在公开的CTW-1500数据集以及自行构建的小文本生成数据集上，将CustomText与现有文本图像生成方法进行对比评估，结果表明其性能更优。
英文摘要：
Textual image generation spans diverse fields like advertising, education, product packaging, social media, information visualization, and branding. Despite recent strides in language-guided image synthesis using diffusion models, current models excel in image generation but struggle with accurate text rendering and offer limited control over font attributes. In this paper, we aim to enhance the synthesis of high-quality images with precise text customization, thereby contributing to the advancement of image generation models. We call our proposed method CustomText. Our implementation leverages a pre-trained TextDiffuser model to enable control over font color, background, and types. Additionally, to address the challenge of accurately rendering small-sized fonts, we train the ControlNet model for a consistency decoder, significantly enhancing text-generation performance. We assess the performance of CustomText in comparison to previous methods of textual image generation on the publicly available CTW-1500 dataset and a self-curated dataset for small-text generation, showcasing superior results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
