Event ·Multi-source

Google 发布 Gemini Omni 1.2 Flash：AI 视频转向可反复修改的创作工具

Google 发布了 Gemini Omni 1.2 Flash，展示 9 个视频生成演示。核心变化在于支持多轮动作迁移、多人对话场景生成，一致性更强。用户可以换角色、换场景、改动作、控制镜头，同时尽量保留原视频的表演和风格，从一次性成片转向可迭代修改的创作流程。

Current read

Google 新出的 Gemini Omni 1.2 Flash 有 9 个演示，视频能改角色换场景还能保留表演，跟之前一次性生成很不一样。

8 sources76° AI heatLast updated 2026/11/6 02:56:12

Evidence

8 sources

Primary sourceAI Will

2026/11/6 02:56:12View source

Related source 1Shubham Saboo

2026/11/5 20:08:54View source

Related source 2Google AI

2026/11/5 17:08:19View source

Related source 3Philipp Schmid

2026/11/5 17:11:33View source

Related source 4Runway ML

2026/11/5 17:54:11View source

Related source 5Decoder

2026/11/5 19:05:31View source

Related source 6lmarena.ai

2026/11/5 19:08:38View source

Related source 7OpenRouter

2026/11/5 20:29:52View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story