从语料库到协同演进的能力：面向通用图像生成的能力中心化数据设计

摘要

大规模图像生成得益于数据规模、质量、再平衡和重新描述方面的进步，然而传统流程通常孤立地优化特定任务的数据集。核心挑战不仅在于如何整理每个任务专属的语料库，还在于如何根据生成能力之间的依赖关系来组织异构监督。我们提出了一种能力驱动的数据基础设施，将能力专属的监督构建与能力对齐的课程调度相结合。其三个专用但互操作的数据引擎为文本-图像基础、图像间变换和图像-知识关联构建互补的关系监督，而描述专家则跨任务和粒度对齐T2I与编辑监督。多阶段课程沿着能力习得的依赖顺序，联合演化任务组成、视觉概念分布、数据质量和图像分辨率；能力感知的评估则通过定向检索、专家构建和差距感知重采样来形成闭环。在大规模场景下，该框架构建了包含4.4亿图像的T2I语料库、1.2亿编辑对和超过2700万图像-实体对。我们利用这一基础设施，从零训练了两个规模的多模态扩散模型，参数量分别为3B和6B。我们在CPI-Bench上进行了定量评估，并在多种文本到图像和编辑场景中进行了定性评估。实验结果表明，该方法具有广泛的视觉覆盖、多样化的渲染能力，并能在生成能力之间有效迁移。

English

Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet conventional pipelines typically optimize task-specific datasets in isolation. A central challenge is not only how to curate each task-specific corpus, but also how to organize heterogeneous supervision according to the dependencies among generative capabilities. We present a capability-driven data infrastructure that couples capability-specific supervision construction with capability-aligned curriculum scheduling. Its three specialized yet interoperable data engines build complementary relational supervision for text-image grounding, inter-image transformation, and image-knowledge association, while caption experts align T2I and editing supervision across tasks and granularities. A multi-stage curriculum jointly evolves task composition, visual-concept distribution, data quality, and image resolution along the dependency order of capability acquisition, with capability-aware evaluation closing the loop through targeted retrieval, expert construction, and gap-aware resampling. At scale, the framework curates a 440M-image T2I corpus, 120M editing pairs, and over 27M image-entity pairs. With this infrastructure, we train multimodal diffusion models at two scales from scratch, with 3B and 6B sizes respectively. We conduct quantitative evaluation on CPI-Bench, along with qualitative evaluations across diverse text-to-image and editing scenarios. Experimental results present broad visual coverage, versatile rendering, and effective transfer across generative capabilities.