Harmonizing Visual Text Comprehension and Generation

In this work, we present TextHarmony, a unified and versatile multimodal generative model proficient in comprehending and generating visual text. Simultaneously generating images and texts typically results in performance degradation due to the inherent inconsistency between vision and language modalities. To overcome this challenge, existing approaches resort to modality-specific data for supervised fine-tuning, necessitating distinct model instances. We propose Slide-LoRA, which dynamically aggregates modality-specific and modality-agnostic LoRA experts, partially decoupling the multimodal generation space. Slide-LoRA harmonizes the generation of vision and language within a singular model instance, thereby facilitating a more unified generative process. Additionally, we develop a high-quality image caption dataset, DetailedTextCaps-100K, synthesized with a sophisticated closed-source MLLM to enhance visual text generation capabilities further. Comprehensive experiments across various benchmarks demonstrate the effectiveness of the proposed approach. Empowered by Slide-LoRA, TextHarmony achieves comparable performance to modality-specific fine-tuning results with only a 2% increase in parameters and shows an average improvement of 2. 5% in visual text comprehension tasks and 4. 0% in visual text generation tasks. Our work delineates the viability of an integrated approach to multimodal generation within the visual text domain, setting a foundation for subsequent inquiries. Code is available at https: //github. com/bytedance/TextHarmony.

Authors

• Zhen Zhao The University of Sydney
• Jingqun Tang ByteDance Inc., Hangzhou, China
• Binghong Wu
• Chunhui Lin
• Shu Wei Institute of Semiconductors, Chinese Academy of Sciences School of Electronic, Electrical, and Communication Engineering, University of Chinese Academy of Sciences
• Hao Liu The Hong Kong University of Science and Technology (Guangzhou) The Hong Kong University of Science and Technology
• Xin Tan East China Normal University, Shanghai, China
• Zhizhong Zhang East China Normal University Shanghai Key Laboratory of Computer Software Evaluating and Testing
• Can Huang ByteDance China
• Yuan Xie East China Normal University, Shanghai, China

Keywords

No keywords are indexed for this paper.