AcFlow：通过学习条件激活流控制文生图扩散Transformer
原标题：AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow
AI 摘要
论文提出 AcFlow，一种在推理阶段控制文本到图像扩散 Transformer（DiT）的方法。它通过一个学习到的、以概念描述为条件的速度场，对中间层图像 token 激活进行传输，同时保持基础 DiT 冻结。该方法支持连续调节风格强度并抑制不需要的概念，在风格-内容权衡上优于基线，且无需针对每个概念单独拟合即可泛化到未见概念。
正文节选
AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow Abstract 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