Google 发布 Gemini Omni 1.2 Flash 视频生成模型
Gemini Omni 1.2 Flash is rolling out starting today to all Google AI subscribers. Refine videos through multi-turn conversational edits and enjoy sharper visual
Gemini Omni 1.2 Flash 从今天起向所有 Google AI 订阅用户推送，在 Gemini 应用中支持多轮对话式视频编辑，并提升了画面稳定性。Google AI Ultra 订阅用户可生成和编辑最长 15 秒的视频。据 Google 介绍，该模型支持 360p 或 720p 草稿生成（$0.07/s）后放大至 1080p 或 4K，成本降低 30%，并支持 3 秒到 15 秒的任意时长、多说话人对话与更连贯的镜头运动。
推荐理由
AI 评分 73
原文列出了视频生成模型在成本、时长和对话式编辑上的具体变化，读者可据此判断视频制作流程会受何影响。
主题
查看原帖认识 Gemini Omni 1.2 Flash，这是我们来自 @GoogleDeepMind 的升级版视频生成模型 🎬 获得更强的一致性、更丰富的创作控制，以及更快、更具成本效益的大规模视频创作： ⚡ 快速且成本降低 30%：以 360p 或 720p（$0.07/s）生成草稿，再放大至 1080p 或 4K ⏱️ 更长的片段：生成和编辑最长 15 秒的视频，或从 3 秒到 15 秒中任选精确时长 💬 对话式编辑：逐轮更换背景、主体或灯光，无需从头开始 🗣️ 更自然的语音：创建流畅的多说话人对话，唇形同步更清晰 🎬 更可控的镜头：指导连续的镜头运动，减少跳切 查看这些更新的实际效果 ↓
查看原文
Meet Gemini Omni 1.2 Flash, our updated video generation model from @GoogleDeepMind 🎬 Get stronger consistency, more creative control, and faster, more cost-effective video creation at scale: ⚡ Fast & 30% lower cost: Draft at 360p or 720p ($0.07/s) and upscale to 1080p or 4K ⏱️ Longer clips: Generate and edit videos up to 15s, or pick any exact length from 3s to 15s 💬 Edit in conversation: Swap backgrounds, subjects, or lighting turn by turn without starting over from scratch 🗣️ More natural speech: Create fluid, multi-speaker dialogue with clearer lip-sync 🎬 More controllable shots: Direct continuous camera moves with fewer jump cuts See these updates in action ↓
正文
Gemini Omni 1.2 Flash is rolling out starting today to all Google AI subscribers. Refine videos through multi-turn conversational edits and enjoy sharper visual stability in the Gemini app.
Plus, Google AI Ultra subscribers can now create and edit videos up to 15 seconds long, giving you more room to tell complete stories, create product explainers, or produce full social ad spots in a single generation.
Learn more about Omni 1.2 Flash in our blog: https://t.co/WY9t7SwWFn