Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models
Alex Jinpeng Wang, Linjie Li, Zhengyuan Yang, Lijuan Wang, Min Li
2025-03-27
Summary
This paper is about creating AI that can generate images with long and coherent text, like paragraphs in a document.
What's the problem?
Current AI models can generate images with short text, but struggle to create images with longer, more complex text.
What's the solution?
The researchers developed a new AI model that is specifically designed to generate images with long text, using a special way to break down the text and images into smaller parts.
Why it matters?
This work matters because it can enable new applications like automatically generating documents and presentations with high-quality images and text.
Abstract
Recent advancements in autoregressive and diffusion models have led to strong performance in image generation with short scene text words. However, generating coherent, long-form text in images, such as paragraphs in slides or documents, remains a major challenge for current generative models. We present the first work specifically focused on long text image generation, addressing a critical gap in existing text-to-image systems that typically handle only brief phrases or single sentences. Through comprehensive analysis of state-of-the-art autoregressive generation models, we identify the image tokenizer as a critical bottleneck in text generating quality. To address this, we introduce a novel text-focused, binary tokenizer optimized for capturing detailed scene text features. Leveraging our tokenizer, we develop \ModelName, a multimodal autoregressive model that excels in generating high-quality long-text images with unprecedented fidelity. Our model offers robust controllability, enabling customization of text properties such as font style, size, color, and alignment. Extensive experiments demonstrate that \ModelName~significantly outperforms SD3.5 Large~sd3 and GPT4o~gpt4o with DALL-E 3~dalle3 in generating long text accurately, consistently, and flexibly. Beyond its technical achievements, \ModelName~opens up exciting opportunities for innovative applications like interleaved document and PowerPoint generation, establishing a new frontier in long-text image generating.