Sign up to save your podcasts
Or
Share SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Diffusion Transformers
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Diffusion Transformers
A 2.6B-parameter open-source world model that generates coherent 720p, minute-long videos with precise 6-DoF camera control on a single GPU using a Hybrid Linear Diffusion Transformer + Gated DeltaNet for long-context efficiency. Targets controllable physics simulation.
View all episodes
By Shaoqing TanA 2.6B-parameter open-source world model that generates coherent 720p, minute-long videos with precise 6-DoF camera control on a single GPU using a Hybrid Linear Diffusion Transformer + Gated DeltaNet for long-context efficiency. Targets controllable physics simulation.