AcFlow：通过学习的条件激活流控制文本到图像扩散Transformer
AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow
- South China University of Technology（华南理工大学）
- Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
AcFlow通过概念条件速度场控制DiT的中间激活，实现风格强度调节和概念抑制，无需训练，性能优于基线。
AI中文摘要：
文本到图像扩散Transformer（DiTs）是强大的生成器，然而直接提示仅提供有限的风格强度控制接口，且可能无法抑制不需要的概念。为了实现这些控制，我们引入了AcFlow，一种推理时控制器，它通过一个学习的概念条件速度场传输中间层图像令牌激活，同时保持基础DiT冻结。文本概念描述指定所需的干预，而积分范围提供连续控制参数。该场产生令牌变化、激活依赖的更新。由于参数在任务族内的概念间共享，该场支持细粒度描述，并泛化到训练中未见过的概念，无需逐概念拟合。在风格控制上，AcFlow在高风格对齐区域中，在评估的基线中实现了最佳的风格-内容权衡。在固定操作点，AcFlow达到风格-内容对齐0.5365/0.2860，而风格对齐最高的基线为0.4397/0.2684。定性结果展示了多样概念的抑制，包括直接提示失败的情况。我们的分析支持学习速度场作为自适应控制机制，更新方向随令牌变化并依赖于其激活状态。我们的代码可在该https URL获取。
英文摘要：
Text-to-image diffusion transformers (DiTs) are powerful generators, yet direct prompting provides limited control interface for style intensity and can fail to suppress unwanted concepts. To enable these controls, we introduce AcFlow, an inference-time controller that transports intermediate layer image-token activations through a learned concept-conditioned velocity field while keeping the base DiT frozen. A textual concept description specifies the desired intervention, while the integration horizon provides a continuous control parameter. The field produces token-varying, activation-dependent updates. With parameters shared across concepts within each task family, one field covers over 15,000 style descriptions or over 1,000 suppression concepts, and generalizes to concepts unseen during training without per-concept fitting. On style control, AcFlow achieves the best style--content trade-off among the evaluated baselines in the high-style-alignment regime. At a fixed operating point, AcFlow attains style--content alignment of 0.5365/0.2860, compared with 0.4397/0.2684 for the baseline with the highest style alignment. On concept suppression, AcFlow reduces the fraction of images showing the concept from 95.3%/82.1% to 41.6%/40.5% on held-in/held-out concepts, including cases where deleting them from the prompt fails to remove them. Our analyses support the learned velocity field as an adaptive control mechanism, with update directions varying across tokens and depending on their activation states. Our code is available at https://github.com/Nove1yst/AcFlow.
