用双层思维链提升文生图质量，让模型像人一样先规划再落笔。
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
- 引入语义与标记两级思维链，分别指导整体构思和像素生成
- 在T2I-CompBench上提升13%，在WISE上提升19%，超越FLUX.1
- 适合追求高精度图像生成的研究者与开发者
大语言模型的进展表明，思维链（CoT）与强化学习（RL）能有效提升性能，但其在视觉生成领域的应用仍不充分。本文提出T2I-R1，一种基于双层思维链推理机制的文生图增强模型。我们识别出两个可优化生成阶段的思维链层次：（1）语义级思维链用于提示词的高层规划；（2）标记级思维链用于逐块生成过程中的低层像素处理。为协调这两级思维链，提出BiCoT-GRPO方法，通过集成生成奖励，在同一训练步骤中联合优化两种推理路径。将该策略应用于基线模型Janus-Pro，实现13%的T2I-CompBench提升与19%的WISE提升，性能超越当前最优模型FLUX.1。代码已公开。
原文摘要 · Abstract (English)
Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning strategies to the visual generation domain remains largely unexplored. In this paper, we present T2I-R1, a novel reasoning-enhanced text-to-image generation model, powered by RL with a bi-level CoT reasoning process. Specifically, we identify two levels of CoT that can be utilized to enhance different stages of generation: (1) the semantic-level CoT for high-level planning of the prompt and (2) the token-level CoT for low-level pixel processing during patch-by-patch generation. To better coordinate these two levels of CoT, we introduce BiCoT-GRPO with an ensemble of generation rewards, which seamlessly optimizes both generation CoTs within the same training step. By applying our reasoning strategies to the baseline model, Janus-Pro, we achieve superior performance with 13% improvement on T2I-CompBench and 19% improvement on the WISE benchmark, even surpassing the state-of-the-art model FLUX.1. Code is available at: https://github.com/CaraJ7/T2I-R1
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。