LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation
Top Cited Papers
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (5) , 5523-5531
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.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Paragraph-to-Image Generation with Information-Enriched Diffusion ModelInternational Journal of Computer Vision, 2025
- Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation2024
- Pedestrian-specific Bipartite-aware Similarity Learning for Text-based Person Retrieval2023
- SPTS v2: Single-Point Scene Text SpottingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation2023
- Compositional Visual Generation with Composable Diffusion Models2022
- Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection2022
- Microsoft COCO: Common Objects in Context2014