Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, especially when it comes to retaining object attributes and relationships. In this paper, we propose CompAgent, a training-free approach for compositional text-to-image generation, with a large language model (LLM) agent as its core. The fundamental idea underlying CompAgent is premised on a divide-and-conquer methodology. Given a complex text prompt containing multiple concepts including objects, attributes, and relationships, the LLM agent initially decomposes it, which entails the extraction of individual objects, their associated attributes, and the prediction of a coherent scene layout. These individual objects can then be independently conquered. Subsequently, the agent performs reasoning by analyzing the text, plans and employs the tools to compose these isolated objects. The verification and human feedback mechanism is finally incorporated into our agent to further correct the potential attribute errors and refine the generated images. Guided by the LLM agent, we propose a tuning-free multi-concept customization model and a layout-to-image generation model as the tools for concept composition, and a local image editing method as the tool to interact with the agent for verification. The scene layout controls the image generation process among these tools to prevent confusion among multiple objects. Extensive experiments demonstrate the superiority of our approach for compositional text-to-image generation: CompAgent achieves more than 10\% improvement on T2I-CompBench, a comprehensive benchmark for open-world compositional T2I generation. The extension to various related tasks also illustrates the flexibility of our CompAgent for potential applications.

翻译：尽管文本到图像模型在生成高质量图像方面取得了显著进展，但面对复杂文本提示时，这些方法仍难以确保文本提示对图像的可控性，尤其是在保留对象属性和关系方面。本文提出了一种无需训练的Compositional Text-to-Image生成方法CompAgent，其核心是一个大型语言模型（LLM）智能体。CompAgent的基本思想基于分而治之的方法论。给定一个包含多个概念（包括对象、属性和关系）的复杂文本提示，LLM智能体首先对其进行分解，包括提取单个对象及其相关属性，并预测连贯的场景布局。这些单个对象随后可被独立处理。接着，智能体通过分析文本进行推理，规划并使用工具组合这些孤立对象。最后，我们将验证与人类反馈机制融入智能体，以进一步修正潜在的属性错误并优化生成图像。在LLM智能体引导下，我们提出了一种无需微调的多概念定制模型和一种布局到图像生成模型作为概念组合的工具，以及一种局部图像编辑方法作为与智能体交互以进行验证的工具。场景布局在这些工具之间控制图像生成过程，以防止多个对象之间的混淆。大量实验证明了我们的方法在组合式文本到图像生成中的优越性：CompAgent在T2I-CompBench（开放世界组合式T2I生成的综合基准）上实现了超过10%的提升。扩展到各种相关任务也展示了CompAgent在潜在应用中的灵活性。