Paper page - SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Source: https://huggingface.co/papers/2605.15178

Abstract

SANA-WM is an efficient 2.6B-parameter world model that generates high-fidelity 720p videos with precise camera control, achieving industrial-level quality while significantly reducing computational requirements through hybrid attention, dual-camera branches, two-stage generation, and robust annotation pipelines.

We introduce SANA-WM, an efficient 2.6B-parameter open-sourceworld modelnatively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with precisecamera control. SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency. Four core designs drive our architecture: (1)Hybrid Linear Attentioncombines frame-wiseGated DeltaNet(GDN) withsoftmax attentionfor memory-efficient long-context modeling. (2) Dual-BranchCamera Controlensures precise6-DoF trajectoryadherence. (3)Two-Stage Generation Pipelineapplies 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 yield high-quality, spatiotemporally consistent action labels. Driven by these designs, SANA-WMdemonstrates remarkable efficiency across data, training compute, and inference hardware: it uses only sim213K public video clips withmetric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60s clip on a single GPU; itsdistilled variantcan be deployed on a single RTX 5090 withNVFP4 quantizationto denoise a 60s 720p clip in 34s. On our one-minute world-model benchmark, SANA-WM demonstrates stronger action-following accuracy than prior open-source baselines and achieves comparable visual quality at 36times higher throughput for scalableworld modeling.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.15178

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.15178 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.15178 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.15178 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.