跳到正文
fal· @fal · X·· 5 小时前AI 评分57
AI 导读

fal 平台上线 Google 的 Gemini Omni Flash 1.2,可从文本、图像或参考片段生成带原生音频的视频。该模型还能用自然语言指令剪辑已有素材、为任意视频续写 3 到 10 秒内容,并将片段超分至 1080p 或 4K,输出最长 15 秒。

正文

Google's Gemini Omni Flash 1.2 is now live on fal.

Generates video with native audio from text, images, or reference clips.
Edits existing footage from a plain-language instruction.
Extends any video with a new 3 to 10 second continuation.
Upscales clips to 1080p or 4K, with outputs up to 15 seconds.

来源:fal · x.com