AI 精选动态
智能评分 75
Google 推出 Gemini Omni Flash API 视频编辑技术
AI 推荐理由
需测试 API 实际能力，但目前缺乏定量基准核心解读
Google DeepMind 宣布 Gemini Omni Flash 可通过 API 获取，支持通过自然语言指令生成和编辑高质量视频，模型版本为 Gemini Omni Flash，参数规模未明确，与 Gemini Image 模型 Nano Banana 2 Lite 同步发布
全文
Mike Taylor-Cai (@miketaylorcai) 转发了 👩💻 Paige Bailey (@DynamicWebPaige) 的帖子：
📽️ We also just made Omni Flash available via the API!
It's uncanny to see how cleanly it can make edits to video using *just* natural language. Test it out in @googleaistudio and @FlowbyGoogle today - which video do you think is the original? 🐕🤖 https://t.co/41n3LviBF0
https://video.twimg.com/amplify_video/2071991919912402946/vid/avc1/1920x1080/1yqV5Px0CwK7cwES.mp4?tag=28
https://video.twimg.com/amplify_video/2071991987323162625/vid/avc1/1280x720/tpJ3OlcoReUrdHC9.mp4?tag=28
https://video.twimg.com/amplify_video/2071992132504801280/vid/avc1/1280x720/L7tkYmO9646w0P-L.mp4?tag=28
https://video.twimg.com/amplify_video/2071992746014035972/vid/avc1/1280x720/-AKMvMIg3qu1UKFl.mp4?tag=28
> **引用原帖 Google DeepMind (@GoogleDeepMind):**
> We’re shipping 2 major releases:
> 🔘 Nano Banana 2 Lite: our fastest and cheapest Gemini Image model
> 🔘 Gemini Omni Flash: now available via the Gemini API and in @GoogleAIStudio to help developers generate and edit high-quality videos.
> https://x.com/GoogleDeepMind/status/2071988044878516466