WorldCast: Distributed Multiplayer World Models

Ziyang Ye¹, Junchao Huang^1,2, Evelyn Zhang², Zhihao Xie¹, Ruicheng Zhang³, Boyao Han¹, Litao Ban⁴, Ziye Wang⁴, Xinting Hu⁵, Shaoshuai Shi⁴, Zhuotao Tian², Li Jiang^1,2†

¹CUHK-Shenzhen  ²SLAI  ³Tsinghua SIGS  ⁴Voyager Research, Didi Chuxing  ⁵USTC  ^†Corresponding author

Project page | Code | Paper (coming soon)

WorldCast is a distributed multiplayer world model. Each player runs a local client, a video generator fine-tuned from Wan2.2-TI2V-5B, on its own GPU. Clients exchange only player states, which each client projects into a camera-aligned player state field, and a shared scene state of generated blocks. This repository holds the weights of the release: the final 4-step model first, with everything the inference code loads beside it.

Files

file	what	dtype	size	sha256
worldcast_4step_bf16.safetensors	the final model: the 4-step student (stage 4, distribution matching distillation, 600 steps), EMA weights; the generator the inference code and the live demo run (paper Table 3)	bf16	10.2 GB	7cfd85b59de04968814a5d560cf6258c91ede0d3a850bd759fe5cc91c5c35b31
state_model.safetensors	the state model: encoder, trunk, action encoder, motion head and place head (paper Sec. 3.4); a client's estimate of its own position from the latents it generates (player_state.source: predicted, live play)	fp32	1.4 GB	86fbf7e11418c568c2a33c8163774b52d1392dde9619e0dc5d9b277251547b23
depth_head.safetensors	picture depth head of the scene state (depth of each generated block)	fp32	176.8 MB	ab599fcd68115142cf3b946e147f3cb89465d0b389371cc3501e1eb3101f6e76
depth_readout.safetensors	read-out of the depth head	fp32	833.4 kB	6994480d726b7e958f519e835fa306b7045cfb19171ade4aebcb594a67ccd873
fixed_prompt_umt5xxl_bf16.safetensors	umT5-XXL embedding of the fixed prompt (the client then skips the 11 GB text encoder)	bf16	4.2 MB	a4157803a2c381835b219c079b7d811b7950c3fb2c47741d4552b7bba37cbd0a
examples/	inputs and expected videos of six recorded rounds (examples/run.sh of the code); listed in examples/manifest.json of the code	-	201.6 MB

The generator file holds EMA weights under the parameter names of the release model (WorldCastGenerator), so a strict load_state_dict works. The inference code needs the five weight files above and nothing else of this repository.

Training checkpoints

EMA weights of the training stages, fp32, under the same names as the generator file; training from them starts from the exact weights. They also hold the visibility probe the training uses (8 tensors).

file	stage	steps	size	sha256
worldcast_stage3_ar_fp32.safetensors	3: block-causal model with scene state (initialises stage 4)	5,000	20.4 GB	a8d39e8b88a0a9e8bd0d65ac804755778ece76839993667055e02eddf878e2c0
worldcast_stage2s_bidirectional_fp32.safetensors	2s: bidirectional model with player state field and scene state (initialises stage 3)	25,000 (20,000 + 5,000)	20.4 GB	83704993f1f6024ce9a4f65987d2dd69dc6172a39a038a3668b2c28dd26fa77b
worldcast_stage2_bidirectional_fp32.safetensors	2: bidirectional model with player state field (initialises stage 2s)	20,000	20.4 GB	3af10355a31e19069dad8a810d38b31cd041c4d5af4460d4d4eb6966af09445e

The training code is in the code repository (tools/train.py, docs/training.md).

Quick start

git clone https://github.com/Ziyang-Ye/WorldCast && cd WorldCast
pip install -e .
python tools/download_weights.py --out-dir weights

This fetches the inference files above, plus the Wan2.2 VAE, tokenizer and config.json from Wan-AI/Wan2.2-TI2V-5B, and writes weights/paths.yaml. Running a session, the examples and the demo, and the options of the download: see the code repository.

License and attribution

• The WorldCast weights are released under the Apache License 2.0.
• They are fine-tuned from Wan2.2-TI2V-5B (Apache License 2.0).
• Training data: the OpenCS2 dataset (CC BY 4.0). The files under examples/ are derived from it.
• The model renders Counter-Strike 2 game content and is intended for research. Counter-Strike 2 is a trademark of Valve Corporation; this work is not affiliated with or endorsed by Valve.

Citation

@article{ye2026worldcast,
  title   = {WorldCast: Distributed Multiplayer World Models},
  author  = {Ye, Ziyang and Huang, Junchao and Zhang, Evelyn and Xie, Zhihao and Zhang, Ruicheng and Han, Boyao and Ban, Litao and Wang, Ziye and Hu, Xinting and Shi, Shaoshuai and Tian, Zhuotao and Jiang, Li},
  journal = {arXiv preprint},
  year    = {2026}
}