TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation 事件

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation arXiv:2605.31590v1 Announce Type: new Abstract: 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 glob