Skip to content
AI News HubLIVE
More
Summary only

NVIDIA Introduces SANA-WM: A 2.6B-Parameter Open-Source World Model That Generates Minute-Scale 720p Video on a Single GPU

NVIDIA's SANA-WM is an open-source world model that generates 60-second 720p video with camera control, trainable on 64 H100s and inferable on a single GPU. Its distilled variant generates a full minute of 720p video in 34 seconds on a single RTX 5090.

SourceMarkTechPostAuthor: Asif Razzaq
NVIDIA Introduces SANA-WM: A 2.6B-Parameter Open-Source World Model That Generates Minute-Scale 720p Video on a Single GPU
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • SANA-WM generates 60-second 720p video from a single image and 6-DoF camera trajectory.
  • Uses hybrid linear attention (Gated DeltaNet) and dual-branch camera control for efficient long-sequence generation.
  • Achieves 36x throughput advantage over prior models while running inference on a single GPU.
  • Open-source, with distilled variant generating a minute of video in 34 seconds on a single RTX 5090.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Chips