InstaGen: Group-Shared Importance Sampling for Fast Video Generation
cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Comments: 13 pages, 6 figures, 2 tables
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: Diffusion Transformers (DiTs) are the dominant architecture for video generation, but their quadratic attention complexity results in substantial computational cost and latency.
Terminology
Abstract
Diffusion Transformers (DiTs) are the dominant architecture for video generation, but their quadratic attention complexity results in substantial computational cost and latency. Permuted block-sparse attention (PBSA) offers a promising approach to reducing this cost by selectively computing blocks of a semantically permuted attention matrix. However, existing approaches typically select only the top few key blocks for each query block, following a top- p paradigm. We find that top- p selection can be highly sample inefficient in high-entropy attention regimes, which are common in video generation. In these regimes, we show that sampling can provide substantially better approximations under the same computational budget. More generally, we cast block selection as importance sampling, where the top-scoring keys form an exact set that is computed in full and the remaining keys are represented by a sample drawn in proportion to their estimated attention and reweighted by inverse sampling probability. Building on this formulation, we present InstaGen, which can be parameterized by any PBSA method: it replaces the method's block selection with an exact set plus a weighted sample. Each query cluster draws one sample shared by all its queries, so the sampled keys form blocks amenable to efficient GPU execution. In this paper, we take the SVG family of PBSA methods and show that, on Wan2.1-T2V-1.3B and Wan2.1-T2V-14B, InstaGen parameterized by SVG2 improves PSNR over SVG2 by 3.4 dB and 2 dB, respectively, at matched attention density, and by 1.6 dB and 2.2 dB at matched wall-clock time. On Wan2.1-T2V-14B, InstaGen also beats SVG-EAR by 1.1 dB PSNR at nearly the same density while running faster (1.65x against 1.48x over dense).
Sources
- SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
- SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
- vAttention: Verified Sparse Attention
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
- Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
- Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
- Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs