Runway 研究实时 AI 视频生成：边描述边直播
原标题：Runway wants to turn AI video generation into a live stream you control in real time
AI 摘要
Runway 公布其实时视频生成研究，用户可在描述过程中直接流式生成视频，而非输入提示词后等待。该方案基于其首个通用世界模型 GWM-1（构建于 Gen-4.5 之上），逐帧生成并接受镜头运动、机器人指令或音频作为控制。Runway 认为实时生成可缩短等待时间、降低 GPU 成本，并将计算负载从训练转向使用；同时指出视频模型逐帧累积误差是核心难题，其通过用自身输出训练模型来纠正偏差。Runway 还展示了与 Nvidia 合作、运行于 Vera Rubin 平台、首帧延迟低于 100 毫秒的实时模型研究预览，但未公布可用时间。
正文节选
Runway wants to turn AI video generation into a live stream you control in real time Runway has shared a look at its research into real-time video generation. Instead of entering a prompt and waiting, users would stream videos as they describe them. Today's video models work in separate steps. You enter a prompt, wait a few seconds or minutes, and get a finished video. If the result isn't right, you start over. Runway says users repeatedly report losing the most time generating and revising vide