让自回归图像生成模型先‘思考’再作图，提升画面质量与一致性。
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
- 用文本推理数据微调模型，让它生成图像前先写‘思考过程’。
- 通过视觉语言模型打分优化，图像生成质量超越现有模型。
- 适合需要精准布局和风格控制的图像生成任务。
尽管思维链推理和强化学习在自然语言处理中取得突破，但其在生成式视觉模型中的应用仍不充分。我们提出ReasonGen-R1，一个两阶段框架：首先通过监督微调，将基于文本的“思考”能力注入自回归图像生成器，训练数据为新生成的、带有文字解释的推理语料；随后利用组相对策略优化（GRPO）进一步精炼输出。为实现模型在生成图像前进行文本推理，我们自动构建并发布了一个包含模型生成的推理文本与视觉提示配对的数据集，支持对物体布局、风格和场景构图的可控规划。我们的GRPO算法采用预训练视觉语言模型提供的奖励信号评估整体视觉质量，在每次更新中优化策略。在GenEval、DPG及T2I基准上的评估表明，ReasonGen-R1持续优于强基线和先前最优模型。
原文摘要 · Abstract (English)
Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues an autoregressive image generator with explicit text-based "thinking" skills via supervised fine-tuning on a newly generated reasoning dataset of written rationales, and then refines its outputs using Group Relative Policy Optimization. To enable the model to reason through text before generating images, We automatically generate and release a corpus of model crafted rationales paired with visual prompts, enabling controlled planning of object layouts, styles, and scene compositions. Our GRPO algorithm uses reward signals from a pretrained vision language model to assess overall visual quality, optimizing the policy in each update. Evaluations on GenEval, DPG, and the T2I benchmark demonstrate that ReasonGen-R1 consistently outperforms strong baselines and prior state-of-the-art models. More: aka.ms/reasongen.
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。