DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-Step Video Diffusion Models.

arXiv:2609.20051v2 Announce Type: replace Abstract: Few-step distillation reduces the inference cost of image-to-video generation, but directly reusing LoRA adapters trained for long denoising trajectories can weaken their intended effects and degrade video qu