**摘要**
Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process, we probe video diffusion transformers (DiTs) and uncover intrinsic turning points in the DiT denoising trajectory where conditioning text affects generation from global layout to fine-grained details. Building on this
👤 作者: Ruotong Liao, Guowen Huang, Qing Cheng, Guangyao Zhai, Lei Zhang, Xun Xiao, Thomas Seidl, Daniel Cremers, Volker Tresp

---
🔗 **[TunerDiT ：用于多事件视频生成的扩散变压器的无需培训的渐进式转向](https://arxiv.org/abs/2605.31590v1)**

> TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-01 14:01