@itsPaulAi: Woow Nvidia has just released a 2.6B open-source world model You can turn a single image, text prompt and trajectory in…

X AI KOLs Timeline Models

Summary

Nvidia released a 2.6B open-source world model that can generate controllable worlds from a single image, text prompt, and trajectory, running on a single GPU.

Woow Nvidia has just released a 2.6B open-source world model You can turn a single image, text prompt and trajectory into controllable worlds... And on a single GPU! - Code available on GitHub - Paper as well on arxiv You can use it for many things like embodied AI and robotics research, simulations, etc. Because it can run on a single GPU (like an RTX 5090 or H100) it makes world models accessible to basically everyone!
Original Article
View Cached Full Text

Cached at: 05/16/26, 07:14 AM

Woow Nvidia has just released a 2.6B open-source world model

You can turn a single image, text prompt and trajectory into controllable worlds…

And on a single GPU!

  • Code available on GitHub
  • Paper as well on arxiv

You can use it for many things like embodied AI and robotics research, simulations, etc.

Because it can run on a single GPU (like an RTX 5090 or H100) it makes world models accessible to basically everyone!

Similar Articles

nvidia/Cosmos3-Super-Text2Image

Hugging Face Models Trending

NVIDIA released Cosmos3-Super-Text2Image, a text-to-image model part of the Cosmos3 omnimodal world model platform for Physical AI, enabling machines to understand and simulate the physical world.

nvidia/Cosmos3-Super-Image2Video

Hugging Face Models Trending

NVIDIA releases Cosmos3-Super-Image2Video, a model that generates temporally coherent video sequences from an input image and text instructions, part of the Cosmos 3 omnimodal world model platform for Physical AI applications.