LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation
Mushui Liu, Yuhang Ma, Zhen Yang, Jun Dan, Yunlong Yu, Zeng Zhao, Zhipeng Hu, Bai Liu
Abstract
Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In this paper, we propose a novel framework called LLM4GEN, which enhances the semantic understanding of text-to-image diffusion models by leveraging the representation of Large Language Models (LLMs). It can be seamlessly incorporated into various diffusion models as a plug-and-play component. A specially designed Cross-Adapter Module (CAM) integrates the original text features of text-to-image models with LLM features, thereby enhancing text-to-image generation. Additionally, to facilitate and correct entity-attribute relationships in text prompts, we develop an entity-guided regularization loss to further improve generation performance. We also introduce DensePrompts, which contains 7,000 dense prompts to provide a comprehensive evaluation for the text-to-image generation task. Experiments indicate that LLM4GEN significantly improves the semantic alignment of SD1.5 and SDXL, demonstrating increases of 9.69% and 12.90% in color on T2I-CompBench, respectively. Moreover, it surpasses existing models in terms of sample quality, image-text alignment, and human evaluation.
BibTeX
@article{Liu_Ma_Yang_Dan_Yu_Zhao_Hu_Liu_Fan_2025, title={LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32588}, DOI={10.1609/aaai.v39i5.32588}, abstractNote={Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In this paper, we propose a novel framework called LLM4GEN, which enhances the semantic understanding of text-to-image diffusion models by leveraging the representation of Large Language Models (LLMs). It can be seamlessly incorporated into various diffusion models as a plug-and-play component. A specially designed Cross-Adapter Module (CAM) integrates the original text features of text-to-image models with LLM features, thereby enhancing text-to-image generation. Additionally, to facilitate and correct entity-attribute relationships in text prompts, we develop an entity-guided regularization loss to further improve generation performance. We also introduce DensePrompts, which contains 7,000 dense prompts to provide a comprehensive evaluation for the text-to-image generation task. Experiments indicate that LLM4GEN significantly improves the semantic alignment of SD1.5 and SDXL, demonstrating increases of 9.69% and 12.90% in color on T2I-CompBench, respectively. Moreover, it surpasses existing models in terms of sample quality, image-text alignment, and human evaluation.}, number={5}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liu, Mushui and Ma, Yuhang and Yang, Zhen and Dan, Jun and Yu, Yunlong and Zhao, Zeng and Hu, Zhipeng and Liu, Bai and Fan, Changjie}, year={2025}, month={Apr.}, pages={5523-5531} }