Matrix-Game
is a 17B-parameter interactive world foundation model for controllable game world generation.
✨ Key Features
🎯
Feature 1
:
Interactive Generation.
A diffusion-based image-to-world model that generates high-quality videos conditioned on keyboard and mouse inputs, enabling fine-grained control and dynamic scene evolution.
🚀
Feature 2
:
GameWorld Score.
A comprehensive benchmark for evaluating Minecraft world models across four key dimensions, including visual quality, temporal quality, action controllability, and physical rule understanding.
💡
Feature 3
:
Matrix-Game Dataset
A large-scale Minecraft dataset with fine-grained action annotations, supporting scalable training for interactive and physically grounded world modeling.
🔥 Latest Updates
[2025-05] 🎉 Initial release of Matrix-Game Model
🚀 Performance Comparison
GameWorld Score Benchmark Comparison
Model
Image Quality ↑
Aesthetic Quality ↑
Temporal Cons. ↑
Motion Smooth. ↑
Keyboard Acc. ↑
Mouse Acc. ↑
3D Cons. ↑
Oasis
0.65
0.48
0.94
0.98
0.77
0.56
0.56
MineWorld
0.69
0.47
0.95
0.98
0.86
0.64
0.51
Ours
0.72
0.49
0.97
0.98
0.95
0.95
0.76
Metric Descriptions
:
Image Quality
/
Aesthetic
: Visual fidelity and perceptual appeal of generated frames
Temporal Consistency
/
Motion Smoothness
: Temporal coherence and smoothness between frames
Keyboard Accuracy
/
Mouse Accuracy
: Accuracy in following user control signals
3D Consistency
: Geometric stability and physical plausibility over time
Please check our
GameWorld
benchmark for detailed implementation.
Human Evaluation
Double-blind human evaluation by two independent groups across four key dimensions:
Overall Quality
,
Controllability
,
Visual Quality
, and
Temporal Consistency
.
Scores represent the percentage of pairwise comparisons in which each method was preferred. Matrix-Game consistently outperforms prior models across all metrics and both groups.
🚀 Quick Start
# clone the repository:
git clone https://github.com/SkyworkAI/Matrix-Game.git
cd Matrix-Game
# install dependencies:
pip install -r requirements.txt
# install apex and FlashAttention-3
# Our project also depends on [apex](https://github.com/NVIDIA/apex) and [FlashAttention-3](https://github.com/Dao-AILab/flash-attention)
# inference
bash run_inference.sh
⭐ Acknowledgements
We would like to express our gratitude to:
Diffusers
for their excellent diffusion model framework
We are grateful to the broader research community for their open exploration and contributions to the field of interactive world generation.
📎 Citation
If you find this project useful, please cite our paper:
@article{zhang2025matrixgame,
title = {Matrix-Game: Interactive World Foundation Model},
author = {Yifan Zhang and Chunli Peng and Boyang Wang and Puyi Wang and Qingcheng Zhu and Zedong Gao and Eric Li and Yang Liu and Yahui Zhou},
journal = {arXiv},
year = {2025}
}
Runs of Skywork Matrix-Game on huggingface.co
54
Total runs
0
24-hour runs
5
3-day runs
-34
7-day runs
-28
30-day runs
More Information About Matrix-Game huggingface.co Model
Matrix-Game huggingface.co is an AI model on huggingface.co that provides Matrix-Game's model effect (), which can be used instantly with this Skywork Matrix-Game model. huggingface.co supports a free trial of the Matrix-Game model, and also provides paid use of the Matrix-Game. Support call Matrix-Game model through api, including Node.js, Python, http.
Matrix-Game huggingface.co is an online trial and call api platform, which integrates Matrix-Game's modeling effects, including api services, and provides a free online trial of Matrix-Game, you can try Matrix-Game online for free by clicking the link below.
Skywork Matrix-Game online free url in huggingface.co:
Matrix-Game is an open source model from GitHub that offers a free installation service, and any user can find Matrix-Game on GitHub to install. At the same time, huggingface.co provides the effect of Matrix-Game install, users can directly use Matrix-Game installed effect in huggingface.co for debugging and trial. It also supports api for free installation.