Skip to content
RobothecaBeta
Log in

LingBot-World

  • AI model
  • Humanoids and robot learning

An open-source world simulator built from video generation, letting users interact with and explore generated environments over time.

Made by Robbyant.

Source on GitHub: github.com/Robbyant/lingbot-world (opens in a new tab). Facts read at commit a43bec7 (opens in a new tab).

Licenses

Code
Apache-2.0 (opens in a new tab)

Read by Robotheca from LICENSE.txt (opens in a new tab) (Apache-2.0) at commit a43bec7 (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Generates high-fidelity, dynamic environments across realistic, scientific, and cartoon styles from an input image and a text prompt.
  • Targets minute-level horizons while keeping context consistent over time, which it calls long-term memory.
  • Supports real-time interaction, reporting latency under one second when producing 16 frames per second.
  • Accepts control signals: camera poses, or actions such as keyboard-style input strings, optionally estimated from video with ViPE.
  • Offers a Base (Cam) model, a Base (Act) model, and a Fast model that uses chunk-by-chunk causal inference with KV caching.
  • Includes a 4-bit quantized Base (Cam) version for inference on GPUs with limited memory, with some loss of visual fidelity.

Written by Robotheca from the project's README (opens in a new tab) at commit a43bec7.

Getting started

Difficulty
Advanced

Maintenance

Status
Maintained: a commit in the last 12 months
Newest commit
9 Jul 2026 on main
Latest release
None published on GitHub

Checked on GitHub on 16 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.