Mini toolsLingBot-World-Base (Act) Preview
By Robbyant
LingBot-World-Base (Act) is a world simulator built on video generation technology, using action control signals to drive scene dynamics. It produces high fidelity, diverse environments spanning realism, scientific contexts, and cartoon styles, while preserving long term memory and contextual consistency over minute length horizons. The model supports real time interactivity with sub 1 second latency at 16 frames per second, generating video at 480P and 720P resolutions from an input image, text prompt, and optional action signals. Built on the Wan2.2 codebase, it is released with open weights and code under the Apache 2.0 license for content creation, gaming, and robot learning research.
Video
Overview
LingBot-World-Base (Act) is an open source world model that generates interactive videos from an image, text prompt, and action control signals. It maintains high fidelity across realistic, scientific, and cartoon environments, supports minute-level long term memory and consistency, and enables real time interactivity with under 1 second latency at 16 frames per second.
Last updated: July 8, 2026
