S $^{2}$ Q-VDiT$^+$: Accurate Quantized Video Diffusion Transformer with Multi-Resolution Sampling and Structural Distillation.
Large-scale video diffusion models (V-DMs) have achieved remarkable text-to-video generation quality, yet their massive computational complexity makes deployment costly. Post-Training Quantization (PTQ) offers an appealing route to accelerate inference without retraining, but existing diffusion PTQ methods remain fragi...