Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912777917956096 |
|---|---|
| author | Wang, Yi Liu, Mushui He, Wanggui Yuan, Hanyang Zhang, Longxiang Huang, Ziwei Zhang, Guanghao Fang, Wenkai Jiang, Haoze Zhang, Shengxuming She, Dong Liu, Jinlong Dai, Weilong Song, Mingli Jiang, Hao Song, Jie |
| author_facet | Wang, Yi Liu, Mushui He, Wanggui Yuan, Hanyang Zhang, Longxiang Huang, Ziwei Zhang, Guanghao Fang, Wenkai Jiang, Haoze Zhang, Shengxuming She, Dong Liu, Jinlong Dai, Weilong Song, Mingli Jiang, Hao Song, Jie |
| contents | Unified generative models have shown remarkable performance in text and image generation. For image synthesis tasks, they adopt straightforward text-to-image (T2I) generation. However, direct T2I generation limits the models in handling complex compositional instructions, which frequently occur in real-world scenarios. Although this issue is vital, existing works mainly focus on improving the basic image generation capability of the models. While such improvements help to some extent, they still fail to adequately resolve the problem. Inspired by Chain of Thought (CoT) solving complex problems step by step, this work aims to introduce CoT into unified generative models to address the challenges of complex image generation that direct T2I generation cannot effectively solve, thereby endowing models with enhanced image generation ability. To achieve this, we first propose Functionality-oriented eXperts (FoXperts), an expert-parallel architecture in our model FoX, which assigns experts by function. FoXperts disentangles potential conflicts in mainstream modality-oriented designs and provides a solid foundation for CoT. When introducing CoT, the first question is how to design it for complex image generation. To this end, we emulate a human-like artistic workflow--planning, acting, reflection, and correction--and propose the Multimodal Chain of Thought (MCoT) approach, as the data involves both text and image. To address the subsequent challenge of designing an effective MCoT training paradigm, we develop a multi-task joint training scheme that equips the model with all capabilities required for each MCoT step in a disentangled manner. This paradigm avoids the difficulty of collecting consistent multi-step data tuples. Extensive experiments show that FoX consistently outperforms existing unified models on various T2I benchmarks, delivering notable improvements in complex image generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01298 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models Wang, Yi Liu, Mushui He, Wanggui Yuan, Hanyang Zhang, Longxiang Huang, Ziwei Zhang, Guanghao Fang, Wenkai Jiang, Haoze Zhang, Shengxuming She, Dong Liu, Jinlong Dai, Weilong Song, Mingli Jiang, Hao Song, Jie Computer Vision and Pattern Recognition Artificial Intelligence Unified generative models have shown remarkable performance in text and image generation. For image synthesis tasks, they adopt straightforward text-to-image (T2I) generation. However, direct T2I generation limits the models in handling complex compositional instructions, which frequently occur in real-world scenarios. Although this issue is vital, existing works mainly focus on improving the basic image generation capability of the models. While such improvements help to some extent, they still fail to adequately resolve the problem. Inspired by Chain of Thought (CoT) solving complex problems step by step, this work aims to introduce CoT into unified generative models to address the challenges of complex image generation that direct T2I generation cannot effectively solve, thereby endowing models with enhanced image generation ability. To achieve this, we first propose Functionality-oriented eXperts (FoXperts), an expert-parallel architecture in our model FoX, which assigns experts by function. FoXperts disentangles potential conflicts in mainstream modality-oriented designs and provides a solid foundation for CoT. When introducing CoT, the first question is how to design it for complex image generation. To this end, we emulate a human-like artistic workflow--planning, acting, reflection, and correction--and propose the Multimodal Chain of Thought (MCoT) approach, as the data involves both text and image. To address the subsequent challenge of designing an effective MCoT training paradigm, we develop a multi-task joint training scheme that equips the model with all capabilities required for each MCoT step in a disentangled manner. This paradigm avoids the difficulty of collecting consistent multi-step data tuples. Extensive experiments show that FoX consistently outperforms existing unified models on various T2I benchmarks, delivering notable improvements in complex image generation. |
| title | Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.01298 |