FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity

arXiv:2605.11869 · cs.CV, cs.LG · Submitted 2026-05-12 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-05-12

Updated: 2026-09-26

Terminology

• Diffusion Model — 24× in this paper · explained in 8 episodes
• Sparsity — 22× in this paper · explained in 4 episodes
• Transformer — 22× in this paper · explained in 2 episodes
• Diffusion Models — 21× in this paper · explained in 6 episodes
• Redundancy — 16× in this paper · explained in 2 episodes
• Consistency — 8× in this paper · explained in 3 episodes
• Frame Interleaved Sparsity — 7× in this paper
• Distillation — 6× in this paper · explained in 2 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Generative Model — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• Latent Diffusion Model — 4× in this paper · explained in 2 episodes
• Latent Diffusion Models — 4× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Predictive Modeling — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Training-Free Framework — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
• $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
• Imagen Video: High Definition Video Generation with Diffusion Models
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
• Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
• Latte: Latent Diffusion Transformer for Video Generation
• MagCache: Fast Video Generation with Magnitude-Aware Cache
• Movie Gen: A Cast of Media Foundation Models
• FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
• Make-A-Video: Text-to-Video Generation without Text-Video Data
• Wan: Open and Advanced Large-Scale Video Generative Models
• AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data
• PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
• VideoLCM: Video Latent Consistency Model
• LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
• Open-Sora: Democratizing Efficient Video Production for All
• MagicVideo: Efficient Video Generation With Latent Diffusion Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models