SparkDiffusion: A Unified Sparse Warm-Up and Few-Step Distillation Framework for Mitigating the High-Sparsity Trap

Video diffusion transformers are central to visual generation, but inference is dominated by attention over long spatiotemporal sequences. While video attention's sparse-plus-low-rank structure suggests high sparsity is possible, existing models degrade beyond $\sim 90\%$ sparsity even after step-local training converges. We identify this failure regime as the high-sparsity trap: step-local objectives leave terminal-visible velocity errors that accumulate during sampling without direct gradient signals to correct them. We propose \method (\methodfull), a unified framework whose central principle is to first adapt a dense video DiT into a high-sparsity coarse prior through sparse warm-up, and then correct its terminal trajectory through few-step trajectory-mixed distillation; fused FP8 kernels provide the deployment layer. Our idealized analysis isolates the mechanism and limits, while experiments validate the staged framework across multiple backbones, tasks, resolutions, and hardware platforms.