@itsPaulAi: Woow Nvidia has just released a 2.6B open-source world model You can turn a single image, text prompt and trajectory in…
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.
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
@svpino: This world generation model is ridiculous. I uploaded a single image (the one on the left), and it created a complete 3…
A user showcases Hyper3D WorldGen, an AI model that generates a complete, editable 3D scene from a single image, highlighting its impressive capabilities.
Genie-style playable world model running 720p at 16 FPS on a single 5090 in 19GB VRAM
ABot-World-0 is a real-time interactive world model that achieves 720p video generation at 16 FPS on a single NVIDIA RTX 5090 GPU with 19GB VRAM, enabling infinite action-conditioned world rollout for simulation and AI research.
nvidia/Cosmos3-Super-Text2Image
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 OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
NVIDIA presents OmniDreams, a generative world model built from the Cosmos diffusion model for real-time action-conditioned video generation, enabling closed-loop simulation for autonomous driving policy evaluation in complex unseen scenarios.
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
ABot-World-0 is a real-time, long-horizon interactive video world model that runs on a single desktop GPU, enabling infinite world rollout with action-conditioned control.