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

• URL: http://arxiv.org/abs/2605.15178v1
• Date: Thu, 14 May 2026 17:58:03 GMT
• Title: SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
• Abstract summary: We introduce SANA-WM, an efficient open-source world model trained for one-minute generation, high-fidelity, 720p, minute-scale videos with precise camera control.<n>SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay.
• Score: 45.09089555026137
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We 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. Four core designs drive our architecture: (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 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 $\sim$213K public video clips with metric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60s clip on a single GPU; its distilled variant can be deployed on a single RTX 5090 with NVFP4 quantization to 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 $36\times$ higher throughput for scalable world modeling.

Related papers

• TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation [105.14745366152725]
  TurboT2VA is a distillation and inference framework for joint text-to-video-audio generation.<n>On LTX-2, four-step distillation reduces generator latency from 50.52s to 2.51s at the standard evaluation resolution of 512$times$768.<n>The complete stack reduces generator latency from 318.74s to 5.83s on one NVIDIA H20, achieving a 54.67$times$ generator-only speedup.
  arXiv  Detail & Related papers  (2026-08-25T15:09:02Z)
• SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation [62.15917923814872]
  We introduce SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales.<n>It matches full-softmax video DiTs in quality while retaining the favorable long-sequence scaling of linear attention.<n>With 40-step sampling, SANA-Video 2.0 achieves a VBench score of 84.30 in 13.2s at 480p on a single H100.
  arXiv  Detail & Related papers  (2026-07-23T17:36:05Z)
• SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer [36.01290871589722]
  Real-time streaming video-to-video editing is critical for interactive applications such as live broadcasting and gaming.<n>We present SANA-Streaming, a system-algorithm co-designed framework for high-resolution, real-time streaming video editing.
  arXiv  Detail & Related papers  (2026-05-28T17:59:17Z)
• DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis [54.19006030081092]
  Trajectory-controlled video generation has become essential for controllable video generation.<n>Existing solutions for extreme-view synthesis typically require dedicated video pairs, demanding substantial annotation effort.<n>We propose Dynamic Extreme VIew Synthesis-GRPO, a GRPO-based framework for trajectory-controlled video generation.
  arXiv  Detail & Related papers  (2026-05-16T11:14:18Z)
• Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising [22.899605451385824]
  We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework.<n>To leverage the strong visual priors of pretrained video diffusion models, X-WAM imagines the future world by predicting multi-view RGB-D videos.<n>Asynchronous Noise Sampling (ANS) to jointly optimize generation quality and action decoding efficiency.
  arXiv  Detail & Related papers  (2026-04-29T14:01:54Z)
• PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation [28.212560558538915]
  We introduce PAM: a Pose-Appearance-Motion Engine for controllable HOI video generation.<n>The performance of our engine is validated by: (1) On DexYCB, we obtain an FVD of 29.13 (vs. 38.83 for InterDyn), and MPJPE of 19.37 mm (vs. 30.05 mm for CosHand)
  arXiv  Detail & Related papers  (2026-03-23T16:51:52Z)
• Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model [52.79436545460808]
  We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation.<n>DaVinci-MagiHuman jointly generates synchronized video and audio using a single-stream Transformer.<n>It supports multilingual spoken generation across Chinese (Mandarin and Cantonese), English, Japanese, Korean, German, and French.
  arXiv  Detail & Related papers  (2026-03-23T13:49:06Z)
• SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer [116.17385614259574]
  We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration.<n>Two core designs ensure our efficient, effective and long video generation.<n>Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models.
  arXiv  Detail & Related papers  (2025-09-29T12:28:09Z)
• xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations [120.52120919834988]
  xGen-SynVideo-1 is a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens. DiT model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios.
  arXiv  Detail & Related papers  (2024-08-22T17:55:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.