ReaDiT Guidance: Control for Image and Video Generation using Diffusion Transformer Features

2026-09-03

AI Summary

该研究提出ReaDiT Guidance框架，通过Diffusion Transformer模型的内部特征表示来控制图像和视频生成，实现根据空间目标如深度、姿态或边缘图进行引导。

Abstract

We present DiT Readout (ReaDiT) Guidance, a lightweight framework for controlling generation with Diffusion Transformer (DiT) models via their internal feature representations. ReaDiT Guidance uses features from a single DiT block to steer the generative process according to spatial targets - like depth, pose, or edge maps - provided at test time. Furthermore, since modern text-to-video models are largely built on DiT backbones, ReaDiT Guidance naturally extends to video generation, enabling camera and motion control. Experimental results demonstrate that our approach achieves competitive or improved results compared to existing feature-based and off-the-shelf adapter-based approaches while requiring fewer parameters.

Problem

• Diffusion Transformer
• Image Generation
• Video Generation
• Feature Control

Innovation

• Diffusion Transformer
• Feature-based Control
• Video Generation
• Lightweight Framework
• Spatial Targets