acvlab/ABot-World-0-5B-LF

🌍 ABot-World: Infinite Interactive World Rollout on Single Desktop GPU

TL;DR: ABot-World turns a single NVIDIA RTX 5090 desktop GPU into a real-time interactive world simulator, enabling infinite action-conditioned world rollout at 720P, 16 FPS, 1.2s latency, and 19GB GPU memory.

🚀 Key Highlights

• 🎮 Action-Driven World Control: Responds to user actions in real time, enabling continuous exploration instead of passive video playback.
• ⚡ Real-Time Desktop Inference: Runs at 720p and 16 FPS on a single NVIDIA RTX 5090 desktop GPU, with 1.2s latency and 19GB GPU memory.
• ♾️ Infinite World Rollout: Supports open-ended interactive world generation beyond fixed video-length limits.
• 🧠 Open-Ended World Imagination: Expands the world with new scenes and dynamics during rollout, avoiding scene lock-in, without prompt switching, by our LongForcing training.

📢 News

• 2026-07-09: We release the causal student model ABot-World-0-5B-LF, inference code, our local gradio demo and online playground ABot World Studio.

🛠️ Setup

This installation was tested on: Ubuntu 22.04, CUDA 13.3, NVIDIA RTX 5090.

1. Clone the repository:

git clone https://github.com/amap-cvlab/ABot-World.git
cd ABot-World

2. Install dependencies using conda:

conda create -n aworld python=3.12 -y
conda activate aworld
pip install -r requirements.txt

3. Download checkpoints:

Download models using HuggingFace:

pip install -U "huggingface_hub"
hf download acvlab/ABot-World-0-5B-LF --local-dir ./checkpoints/ABot-World-0-5B-LF

Download models using ModelScope:

pip install -U "modelscope"
modelscope download "amap_cvlab/ABot-World-0-5B-LF" --local_dir ./checkpoints/ABot-World-0-5B-LF

After downloading, the project should have the following checkpoint structure:

checkpoints/
└── ABot-World-0-5B-LF/
    ├── Wan2.2_VAE.pth
    ├── taew2_2.pth
    ├── models_t5_umt5-xxl-enc-bf16.pth
    ├── diffusion_pytorch_model.safetensors
    └── google/umt5-xxl/

The checkpoint paths are configured in configs/long_forcing_dmd.yaml and configs/default_config.yaml. The distilled generator weights are already merged into ABot-World-0-5B-LF/diffusion_pytorch_model.safetensors.

🤗 Gradio Demo

bash web_client/run.sh

Select a GPU with:

CUDA_ID=0 bash web_client/run.sh

License

This project is released under the Apache License 2.0. See LICENSE, NOTICE, and THIRD_PARTY_NOTICES.md for copyright and third-party attribution details.

🤝 Acknowledgement

This project builds on and is inspired by the following open-source projects: Causal Forcing, AngelSlim, LightX2V, taehv, Wan2.2, Helios, from which the optimized Triton RoPE and normalization kernels in wan/modules/helios_kernels are derived.

🗓️ Roadmap

• Interactive Web Playground (ABot World Studio)
• Inference Code Release
• Local Gradio Demo Release
• Causal Student Model Release
• Bidirectional Teacher Model Release
• Technical Report (Arxiv)

📝 Citation

If you find our work helpful, please cite our paper:

@article{abot-world-0,
      title={ABot-World-0: Infinite Interactive World Rollout on Single Desktop GPU}, 
      author={ABot-World Team},
      year={2026}
}