Interleaving Reasoning for Better Text-to-Image Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912577756332032 |
|---|---|
| author | Huang, Wenxuan Chen, Shuang Xie, Zheyong Cao, Shaosheng Tang, Shixiang Shen, Yufan Yin, Qingyu Hu, Wenbo Wang, Xiaoman Tang, Yuntian Qiao, Junbo Guo, Yue Hu, Yao Yin, Zhenfei Torr, Philip Cheng, Yu Ouyang, Wanli Lin, Shaohui |
| author_facet | Huang, Wenxuan Chen, Shuang Xie, Zheyong Cao, Shaosheng Tang, Shixiang Shen, Yufan Yin, Qingyu Hu, Wenbo Wang, Xiaoman Tang, Yuntian Qiao, Junbo Guo, Yue Hu, Yao Yin, Zhenfei Torr, Philip Cheng, Yu Ouyang, Wanli Lin, Shaohui |
| contents | Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly couple comprehension with generation such as GPT-4o. Motivated by recent advances in interleaving reasoning, we explore whether such reasoning can further improve Text-to-Image (T2I) generation. We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis: the model first produces a text-based thinking to guide an initial image, then reflects on the result to refine fine-grained details, visual quality, and aesthetics while preserving semantics. To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals: (1) strengthening the initial think-and-generate stage to establish core content and base quality, and (2) enabling high-quality textual reflection and faithful implementation of those refinements in a subsequent image. We curate IRGL-300K, a dataset organized into six decomposed learning modes that jointly cover learning text-based thinking, and full thinking-image trajectories. Starting from a unified foundation model that natively emits interleaved text-image outputs, our two-stage training first builds robust thinking and reflection, then efficiently tunes the IRG pipeline in the full thinking-image trajectory data. Extensive experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN, alongside substantial improvements in visual quality and fine-grained fidelity. The code, model weights and datasets will be released in: https://github.com/Osilly/Interleaving-Reasoning-Generation . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06945 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interleaving Reasoning for Better Text-to-Image Generation Huang, Wenxuan Chen, Shuang Xie, Zheyong Cao, Shaosheng Tang, Shixiang Shen, Yufan Yin, Qingyu Hu, Wenbo Wang, Xiaoman Tang, Yuntian Qiao, Junbo Guo, Yue Hu, Yao Yin, Zhenfei Torr, Philip Cheng, Yu Ouyang, Wanli Lin, Shaohui Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly couple comprehension with generation such as GPT-4o. Motivated by recent advances in interleaving reasoning, we explore whether such reasoning can further improve Text-to-Image (T2I) generation. We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis: the model first produces a text-based thinking to guide an initial image, then reflects on the result to refine fine-grained details, visual quality, and aesthetics while preserving semantics. To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals: (1) strengthening the initial think-and-generate stage to establish core content and base quality, and (2) enabling high-quality textual reflection and faithful implementation of those refinements in a subsequent image. We curate IRGL-300K, a dataset organized into six decomposed learning modes that jointly cover learning text-based thinking, and full thinking-image trajectories. Starting from a unified foundation model that natively emits interleaved text-image outputs, our two-stage training first builds robust thinking and reflection, then efficiently tunes the IRG pipeline in the full thinking-image trajectory data. Extensive experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN, alongside substantial improvements in visual quality and fine-grained fidelity. The code, model weights and datasets will be released in: https://github.com/Osilly/Interleaving-Reasoning-Generation . |
| title | Interleaving Reasoning for Better Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.06945 |