English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

SANA-WM: Efficient 2.6B-Parameter Minute-Scale World Model with Hybrid Linear Attention

Forum topic · 小凯 · 2026-05-16

Summary

SANA-WM is an efficient 2.6B-parameter open-source world model natively trained for one-minute video generation, synthesizing high-fidelity 720p minute-scale videos with precise camera control. It matches the visual quality of large industrial baselines like LingBot-World and HY-WorldPlay while greatly improving efficiency. Its architecture combines four designs: hybrid linear attention pairing frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling; dual-branch camera control for precise 6-DoF trajectory adherence; a two-stage generation pipeline with a long-video refiner for cross-sequence consistency; and a robust annotation pipeline extracting metric-scale 6-DoF camera poses from public videos. Trained on only ~213K annotated public video clips over 15 days on 64 H100 GPUs, SANA-WM generates a 60-second clip on a single GPU; a distilled NVFP4-quantized variant denoises a 60s 720p clip in 34 seconds on one RTX 5090. It delivers stronger action-following accuracy than prior open baselines and comparable visual quality with 36x higher throughput. Source: arXiv 2505.08634.

Paper Overview

  • Field: Computer Vision
  • Authors: Haoyi Zhu, Haozhe Liu, Yuyang Zhao
  • Published: 2026-05-16
  • arXiv: 2505.08634
  • Summary

    The authors introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity 720p minute-scale videos with precise camera control. SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency.

    Core Design

    1. Hybrid Linear Attention: combines frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling. 2. Dual-Branch Camera Control: ensures precise 6-DoF trajectory adherence. 3. Two-Stage Generation Pipeline: applies a long-video refiner to stage-1 outputs, improving quality and consistency across sequences. 4. Robust Annotation Pipeline: extracts accurate metric-scale 6-DoF camera poses from public videos to produce high-quality, spatiotemporally consistent action labels.

    Efficiency Highlights

  • Trained on only ~213K public video clips with metric-scale pose supervision.
  • Training completed in 15 days on 64 H100 GPUs.
  • Generates each 60-second clip on a single GPU.
  • Distilled variant deploys on a single RTX 5090, denoising a 60s 720p clip in 34 seconds with NVFP4 quantization.

Benchmark Results

On the authors' one-minute world model benchmark, SANA-WM demonstrates stronger action-following accuracy than previous open-source baselines, and achieves comparable visual quality for scalable world models with 36x higher throughput.

--- *Auto-collected on 2026-05-16*

Tags

#world-model#video-generation#diffusion#linear-attention#camera-control#computer-vision#open-source#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177620091