语义浏览：图像生成中的可控多样性

摘要

现代文本到图像模型在视觉保真度和提示遵循方面表现出色。然而，这种严格的遵循是以牺牲多样性为代价的：生成的样本往往坍缩为单一的视觉解释。现有的提高多样性的方法产生的输出由偶然变化驱动，而非有意义的设计选择。这催生了一个新的多样性任务变体，即对生成样本施加结构约束。我们提出了一种用于受控多样性的方法，实现了语义浏览——用户可以通过系统遍历有意义、可解释的变化轴，在结构化图像画廊中导航，体验创造性探索。实现这种语义控制水平需要对场景有深刻理解。我们利用了近期文本到图像模型在详细描述上训练的事实，有效将语义决策与像素生成解耦。这带来了范式转变：不再依赖文本到图像模型内部的随机变化，而是直接在文本层面诱导多样性。通过利用丰富的文本表示，我们允许视觉语言模型（VLM）在完整的场景上下文中运行。为克服标准VLM典型的通用输出，我们采用代理工作流，明确强制实施与原始提示相契合的结构化变化。我们证明了该方法能生成多样且可导航的设计空间，其中每个变化都对应一个特定的、用户可理解的语义决策。

English

Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a single visual interpretation. Existing methods to improve diversity produce outputs driven by incidental variations rather than meaningful design choices. This motivates a new variant of the diversity task where structure is enforced on the generated samples. We introduce a method for controlled diversity that enables Semantic Browsing, where users can navigate structured image galleries and experience creative exploration through a systematic traversal of meaningful, interpretable axes of variation. Achieving this level of semantic control requires a deep understanding of the scene. We exploit the fact that recent text-to-image models are trained on elaborated captions, effectively decoupling semantic decision-making from pixel generation. This enables a paradigm shift: instead of relying on stochastic variation within the text-to-image model, we induce diversity directly at the text level. By leveraging rich textual representations, we allow a Vision Language Model (VLM) to operate on the full scene context. To overcome the generic outputs typical of standard VLMs, we employ an agentic workflow that explicitly enforces structured variation attuned to the original prompt. We demonstrate that our method produces diverse and navigable design spaces where every variation corresponds to a specific, user-understandable semantic decision.