跳到正文
𝕏 Rohan Paul(x.com)·· 12 天前品質評分60
重點導讀

PAN 2 是一款免費、開放的動作條件世界模型,可根據描述的動作生成最長 20 秒、呈現後續物理變化的影片。

  • 生成方式:語言模型先規劃情節,再由 29B 影片模型生成畫面。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

Rohan Paul
Rohan Paul@rohanpaul_ai
·12 天前
𝕏

Agents learn from trial and error. The expensive part is the error.
A world model moves the error into simulation, which is the whole case for something like PAN 2.

This is a free, open "action-conditioned world model".

Takes an action you describe, and generates up to 20 seconds of video showing what would physically happen next. Its new trick is splitting the job in 2: a language model first works out the plot, then a 29B video model renders it.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論