DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention

arXiv:2609.32628 · cs.CV, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/anemoi-project/anemoi

Terminology

• Quantization — 49× in this paper · explained in 12 episodes
• Sparsity — 26× in this paper · explained in 4 episodes
• Fidelity — 8× in this paper · explained in 2 episodes
• Sparse Attention — 8× in this paper · explained in 5 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 2× in this paper
• Clustering — 2× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 2× in this paper
• Training-Free Framework — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition Workshops — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Error Decomposition — 1× in this paper · explained in 3 episodes

Sources

• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
• Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
• ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention
• DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance
• Wan: Open and Advanced Large-Scale Video Generative Models
• XAttention: Block Sparse Attention with Antidiagonal Scoring
• SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

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