# Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation

arXiv: https://arxiv.org/abs/2401.15688 · HTML: https://mlsanity.com/paper/2401.15688/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 28 Jan 2024.

## Builds on (most cited first, 29 of 29)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [Cones 2: Customizable Image Synthesis with Multiple Subjects](https://mlsanity.com/paper/2305.19327/) (2023)
- [InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language](https://mlsanity.com/paper/2305.05662/) (2023)
- [Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models](https://mlsanity.com/paper/2305.13921/) (2023)
- [TokenCompose: Text-to-Image Diffusion with Token-level Supervision](https://mlsanity.com/paper/2312.03626/) (2023)
- [ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations](https://mlsanity.com/paper/2312.04655/) (2023)

## Built on by (most cited first, 4 of 4)

- [LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration](https://mlsanity.com/paper/2504.00010/) (2025)
- [GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration](https://mlsanity.com/paper/2412.04440/) (2024)
- [Marmot: Object-Level Self-Correction via Multi-Agent Reasoning](https://mlsanity.com/paper/2504.20054/) (2025)
- [Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models](https://mlsanity.com/paper/2607.16409/) (2026)

## Abstract (arXiv)

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.