IT之家 AI

Kunlun Wanwei releases the world's first consumer-grade graphics card video large model game, and opens it up for open source use

IT Home reported on October 15 that Kunlun Wanwei released today the world’s first video large-scale game running on a single consumer-grade graphics card — Matrix-Game 4.0. According to Kunlun Wanwei, “Matrix-Game 4.0…

Image
Image source · IT之家 AI

IT Home On October 15, Kunlun Wanyi released the world’s first video large model game running on a single consumer-grade graphics card — Matrix-Game 4.0.

Image

Kunlun Wanwei stated, “Matrix-Game 4.0 has established a new paradigm for game world modeling: the game engine maintains the world state and interaction rules, while the video-generated model presents a detailed image in real time. It packs a real-time gaming experience of 480p and 60 FPS into a NVIDIA RTX 5090; from when you press a button to when the image responds, the delay is less than 150 milliseconds.” Matrix-Game 4.0 has successfully completed the full closed loop of ‘code generation for game logic → structural visuals providing structural constraints → real-time rendering of video models’, enabling a truly practical technical path for game prototype development, personalized customization, and UGC. The project has been opened source simultaneously.

IT Home notes that Matrix-Game 4.0 was made open source at the time of release. In the future, the team will continue to iterate the model: deploying a refiner to improve image resolution, exploring a multi-player experience with consistent perspectives across players, providing finer-grained image control, and expanding support for more game types and scenarios.

Open-source address and project website:

Github: https://github.com/SkyworkAI/Matrix-Game.git

Huggingface: https://huggingface.co/Skywork/Matrix-Game-4.0

Project website: https://matrix-game-v4-0.github.io/page/

Ad notice: The text contains external link references (including but not limited to hyperlinks, QR codes, passwords, etc.) designed to provide more information, save selection time, and the results are for reference only. Articles on IT Home that include external links comply with this notice.

Original source

IT之家 AI

Content notes

Original publication and rights belong to the source.

Machine translation · Refer to the original