LingBot-World 2.0: Interactive world generation from image, text, and actions

LingBot-World 2.0 (LingBot-World-Infinity) introduces unbounded interaction horizons, rapid 60fps 720p video generation, diverse interactive elements, and an agentic harness for world modeling. The real-time version is available on Reactor and LingGuang platforms, with the official demo at WAIC 2026.

We present LingBot-World 2.0 also known as LingBot-World-Infinity , an advanced iteration of LingBot-World https://technology.robbyant.com/lingbot-world featuring four distinct upgrades. Unbounded Interaction Horizon : Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. Rapid Response Time : Through distilling a real-time variant from the base model, our system guarantees rapid response time, sufficient to drive 720p video streams at 60 fps. Highly Diverse Interactive Elements : Compared to the previous version, this update introduces highly diverse interactive elements, comprising a broader spectrum of actions e.g. , attacking, archery, spell-casting, and shooting alongside a richer variety of text-driven events. Agentic Harness : We pioneer the integration of an agentic harness within the domain of world modeling, wherein a pilot agent is tasked with planning and executing character behaviors, while a director agent is responsible for synthesizing novel environmental elements as the scene progresses. The real-time version of LingBot-World-Infinity is available on two platforms. We thank Reactor https://www.reactor.inc/lingbot-world-v2 and LingGuang https://www.lingguang.com/support for their support: Note:Reactor and LingGuang provide a convenient way to try LingBot-World-Infinity in real time. In our official setup, the model runs at full capability. To experience our official demo, join us at WAIC 2026 . portal.mp4 beauty.mp4 chair.mp4 shooting.mp4 room.mp4 dinosaur.mp4 ✨ For more high-fidelity and compelling demos, please visit our Project Page. - Jul. 9, 2026: 🎉 We release the technical report, inference code, and models for LingBot-World-Infinity. - Release the causal-fast inference code and model of the 14B model - Release the causal-pretrained model of the 14B model - Release the bidirectional model of the 14B model - Release the causal-fast and causal-pretrained models of the 1.3B model This codebase is built upon Wan2.2 https://github.com/Wan-Video/Wan2.2 . Please refer to their documentation for installation instructions. Clone the repo: git clone https://github.com/robbyant/lingbot-world-v2.git cd lingbot-world-v2 Install dependencies: Ensure torch = 2.4.0 pip install -r requirements.txt Install flash attn https://github.com/Dao-AILab/flash-attention : pip install flash-attn --no-build-isolation | Model | Model Type | Model Size | Download Links | |---|---|---|---| lingbot-world-v2-14b-causal-fast | causal-fast | 14B | 🤗 | lingbot-world-v2-14b-causal-pretrain Download models using huggingface-cli: pip install "huggingface hub cli " huggingface-cli download robbyant/lingbot-world-v2-14b-causal-fast --local-dir ./lingbot-world-v2-14b-causal-fast Download models using modelscope-cli: pip install modelscope modelscope download robbyant/lingbot-world-v2-14b-causal-fast --local dir ./lingbot-world-v2-14b-causal-fast We provide generate.py for causal inference with KV caching, which processes video frames chunk-by-chunk instead of all at once. causal fast — 480P, multi-GPU: torchrun --nproc per node=8 generate.py --task i2v-A14B --size 480 832 --ckpt dir lingbot-world-v2-14b-causal-fast --image examples/03/image.jpg --action path examples/03 --dit fsdp --t5 fsdp --ulysses size 8 --frame num 361 --local attn size 18 --sink size 6 --prompt "A serene lakeside scene with a lone tree standing in calm water, surrounded by distant snow-capped mountains under a bright blue sky with drifting white clouds — gentle ripples reflect the tree and sky, creating a tranquil, meditative atmosphere." You can also use the provided run fast.sh script: bash run fast.sh <weights dir <frame num e.g. bash run fast.sh lingbot-world-v2-14b-causal-fast 361 We do NOT plan to release our deployment code. If you would like to deploy our model yourself, please refer to the LingBot-World deployment in SGLang https://docs.sglang.io/cookbook/diffusion/LingBot-World/LingBot-World-2.0 or flashdreams https://github.com/NVIDIA/flashdreams . This project is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License CC BY-NC-SA 4.0 . The project is available for non-commercial use only: you may share and adapt it with proper attribution, but derivative works must be distributed under the same license. Please refer to the LICENSE file /Robbyant/lingbot-world-v2/blob/main/LICENSE.txt for the full text, including details on rights and restrictions. We would like to express our gratitude to the Wan Team for open-sourcing their code and models. Their contributions have been instrumental to the development of this project. If you find this work useful for your research, please cite our paper: @article{lingbot-world-v2, title={Infinite Worlds with Versatile Interactions}, author={Zelin Gao and Qiuyu Wang and Jiapeng Zhu and Jingye Chen and Zichen Liu and Qingyan Bai and Jiahao Wang and Yufeng Yuan and Hanlin Wang and Yichong Lu and Ka Leong Cheng and Haojie Zhang and Jian Gao and Tianrui Feng and Yuzheng Liu and Yao Yao and Yinghao Xu and Xing Zhu and Yujun Shen and Hao Ouyang}, journal={arXiv preprint arXiv:2607.07534}, year={2026} }