In this work, we study the problem of Text-to-Image In-Context Learning (T2I-ICL). While Unified Multimodal LLMs (MLLMs) have advanced rapidly in recent years, they struggle with contextual reasoning in T2I-ICL scenarios. To address this limitation, we propose a novel framework that incorporates a thought process called ImageGen-CoT prior to image generation. To avoid generating unstructured ineffective reasoning steps, we develop an automatic pipeline to curate a high-quality ImageGen-CoT dataset. We then fine-tune MLLMs using this dataset to enhance their contextual reasoning capabilities. To further enhance performance, we explore test-time scale-up strategies and propose a novel hybrid scaling approach. This approach first generates multiple ImageGen-CoT chains and then produces multiple images for each chain via sampling. Extensive experiments demonstrate the effectiveness of our proposed method. Notably, fine-tuning with the ImageGen-CoT dataset leads to a substantial 80\% performance gain for SEED-X on T2I-ICL tasks. See our project page atthis https URL. Code and model weights will be open-sourced.
View on arXiv@article{liao2025_2503.19312,
title={ ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning },
author={ Jiaqi Liao and Zhengyuan Yang and Linjie Li and Dianqi Li and Kevin Lin and Yu Cheng and Lijuan Wang },
journal={arXiv preprint arXiv:2503.19312},
year={ 2025 }
}