Real-time interactive world model from Robbyant that generates controllable, long-horizon environments.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
LingBot-World 2.0 (also referred to as LingBot-World-Infinity on the official page) is an interactive world model from Robbyant. It generates environments that users can move through, look around in and act on, with real-time inference and sub-second latency according to the vendor. Creator coverage describes control via key presses and prompts at 720p and 60fps, with worlds sustained for over an hour.
The vendor lists several capabilities: multi-user shaping of one world (one user as player, another as director), support for agent-driven behaviour and user-directed events (creator coverage mentions NPC agents), and long exploration without visual drift. It is also positioned beyond game-like scenes, as a foundation for embodied and robotic simulation, future-state prediction and interactive data generation, learned from egocentric, synthetic and web-scale video.
Creators report it is built on Wan 2.2, with 14B and 1.3B variants released; this was not confirmed on the scraped page, and no repository, model card or licence was provided. The vendor acknowledges open challenges: true long-term world memory, extended interactions and faithful physical understanding.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Real-time interactive world model controlled by key presses and prompts, running at 720p 60fps and generating worlds for over an hour. Adds NPC agents, built on Wan 2.2, with 14B and 1.3B variants released.
Open-ended interactive world model running in real time at 720p and 60 fps, responding to key presses and specified events. The fast inference model is released at 86 GB, so it needs multiple GPUs.
Closest neighbours by meaning, not just by category.
Model
14B autoregressive world model that generates interactive, camera-controlled video worlds in 3 denoising steps.
Model
Real-time interactive world model with compressed memory and hybrid action and semantic control, built on Wan 2.2.
Model · Runway
Runway's real-time interactive world model generating 720p/24fps video with audio, steered by text actions and camera input.
Model · Google DeepMind
Google DeepMind world model that turns text or images into interactive, real-time controllable worlds with audio.
Model
Interactive autoregressive world model generating minute-long playable video with real-time camera control and prompt events.
Model
Interactive world model that generates action-conditioned video rollouts in real time on a single RTX 5090.