Expressive Text-to-Image Generation with Rich Text

TL;DR

This paper introduces a rich-text interface for text-to-image generation, enabling detailed control over style, color, and regions, thus improving customization and fidelity in generated images.

Contribution

It proposes a novel region-based diffusion method that leverages rich text attributes for precise and detailed image synthesis, surpassing previous plain text approaches.

Findings

Outperforms baseline methods in quantitative evaluations.

Enables explicit control over style and color in generated images.

Demonstrates detailed region-specific image synthesis capabilities.

Abstract

Plain text has become a prevalent interface for text-to-image synthesis. However, its limited customization options hinder users from accurately describing desired outputs. For example, plain text makes it hard to specify continuous quantities, such as the precise RGB color value or importance of each word. Furthermore, creating detailed text prompts for complex scenes is tedious for humans to write and challenging for text encoders to interpret. To address these challenges, we propose using a rich-text editor supporting formats such as font style, size, color, and footnote. We extract each word's attributes from rich text to enable local style control, explicit token reweighting, precise color rendering, and detailed region synthesis. We achieve these capabilities through a region-based diffusion process. We first obtain each word's region based on attention maps of a diffusion process using plain text. For each region, we enforce its text attributes by creating region-specific detailed prompts and applying region-specific guidance, and maintain its fidelity against plain-text generation through region-based injections. We present various examples of image generation from rich text and demonstrate that our method outperforms strong baselines with quantitative evaluations.