Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models
This addresses a critical gap in text-to-image systems for applications like document and slide generation, though it is incremental as it builds on existing autoregressive and diffusion models.
The paper tackles the problem of generating coherent long-form text in images, such as paragraphs, by introducing a novel text-focused binary tokenizer and a multimodal autoregressive model, achieving significant improvements over state-of-the-art models like SD3.5 Large and GPT4o with DALL-E 3 in accuracy, consistency, and flexibility.
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~\cite{sd3} and GPT4o~\cite{gpt4o} with DALL-E 3~\cite{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.