核心信息
fal 发布了 H3 Max Director，据称是首个原生连续、实时的前沿视频模型，用于动作控制的长视频生成。与之前拼接离散片段的模型不同，它以单一连续视频流随时间保持上下文，并驱动 fal 的实验性无限 AI 直播。
要点
- 生成单一连续视频流，而非拼接多个片段，从而保持时间上下文。
- 支持动作控制的长视频生成，并具备实时交互能力。
- 驱动实验性无限 AI 直播，观众可实时影响生成内容。
fal 发布 H3 Max Director：连续实时视频生成
原始推文
RT @fal: Introducing fal's H3 Max Director, the first natively continuous real-time frontier video model for action-controlled long-form generation. Unlike H3 Max and other video models, H3 Max Director generates a single continuous video stream, maintaining context over time rather than chaining together discrete clips. It’s the technology behind https://t.co/5BhqcfNMDW, our experimental infinite AI livestream where viewers interact with and shape what gets generated in real time. Now, we’re making the underlying model available via API. For the first two weeks, all H3 Max Director generations are 75% off.