CustomText: Customized Textual Image Generation using Diffusion Models
This work addresses the need for better text rendering and control in image generation for applications like advertising and branding, but it is incremental as it builds on existing models like TextDiffuser and ControlNet.
The paper tackled the problem of generating high-quality images with precise text customization, which current diffusion models struggle with, and achieved superior results on the CTW-1500 dataset and a self-curated small-text dataset.
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.