Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

本文为原文前 6,000 字符的节选翻译，完整内容请查看原文。

Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips Nov 05, 2026 | x.com Facebook LinkedIn Mail Copy link Gemini Omni 1.2 Flash brings 15-second clips, stronger consistency, and faster, more cost-effective generation. Anish Nangia Product Manager, Google DeepMind Share x.com Facebook LinkedIn Mail Copy link Your browser does not support the audio element. Listen to article [[duration]] minutes This content is generated by Google AI. Generative AI is experimental Voice Speed Voice Speed 0.75X 1X 1.5X 2X Read AI-generated summary We’re rolling out Gemini Omni 1.2 Flash, which offers native 15-second video creation, improved reference adherence, and multi-turn conversational editing. This update lowers costs by 30% and provides better consistency for your professional projects. You can start using these capabilities today across the Gemini API, Google Vids, and Gemini for business to produce high-quality video content at scale.

Gemini Omni 1.2 Flash：更快速、更具成本效益且支持更长片段，2026年11月5日。Gemini Omni 1.2 Flash 带来了 15 秒的视频片段、更强的连贯性以及更快、更具成本效益的生成能力。Google DeepMind 产品经理 Anish Nangia 表示，我们正在推出 Gemini Omni 1.2 Flash，它提供原生 15 秒视频创作、改进的参考遵循能力以及多轮对话编辑功能。此次更新将成本降低了 30%，并为您的专业项目提供了更好的连贯性。您今天就可以在 Gemini API、Google Vids 和 Gemini for business 中使用这些功能，大规模制作高质量的视频内容。

Summaries were generated by Google AI. Generative AI is experimental. We are launching Gemini Omni 1.2 Flash with support for fifteen-second videos and improved reference adherence. You can now edit clips through multi-turn conversations, which allows for faster adjustments without starting over. We reduced the price by 30% to help you produce high-quality video content at a lower cost. This model is generally available on the Gemini API and Google Cloud for your production needs.

摘要由 Google AI 生成。生成式 AI 处于实验阶段。我们正在推出支持 15 秒视频和改进参考遵循能力的 Gemini Omni 1.2 Flash。您现在可以通过多轮对话编辑片段，无需从头开始即可进行更快的调整。我们将价格降低了 30%，以帮助您以更低的成本制作高质量的视频内容。该模型现已在 Gemini API 和 Google Cloud 上全面可用，以满足您的生产需求。

Today, we’re rolling out Gemini Omni 1.2 Flash, and making it generally available across the Gemini API and Gemini for business. Gemini Omni 1.2 Flash introduces native 15-second video creation, multi-turn conversational editing capabilities, and enhanced reference following. We have dropped the price 30% from Gemini Omni 1.1 making it available at $0.07 per second for 720p video. Here’s an overview of what’s new: Fast and cost-effective at scale. Beyond the lower price, the workflow keeps costs down: you can draft fast at 360p or 720p, fix a detail with a follow-up edit instead of re-generating the entire clip, and then upscale your best creations to 1080p or 4K.

今天，我们正式推出 Gemini Omni 1.2 Flash，并使其在 Gemini API 和 Gemini for business 中全面可用。Gemini Omni 1.2 Flash 引入了原生 15 秒视频创作、多轮对话编辑功能以及增强的参考遵循能力。我们将价格较 Gemini Omni 1.1 下调了 30%，720p 视频的价格现为每秒 0.07 美元。以下是新功能的概述：大规模快速且具成本效益。除了更低的价格外，工作流程也降低了成本：您可以先以 360p 或 720p 快速起草，通过后续编辑修复细节，而不是重新生成整个片段，然后再将您最满意的作品提升至 1080p 或 4K。

Longer clips up to 15 seconds. You can now generate and edit videos natively up to 15 seconds long, up from 10 seconds with Omni 1.1. You can also specify duration in one-second increments from 3 to 15 seconds, giving you room to tell complete stories, create product explainers, or produce full social ad spots in a single generation.

最长 15 秒的视频片段。您现在可以原生生成和编辑长达 15 秒的视频，高于 Omni 1.1 的 10 秒。您还可以以 1 秒为增量指定 3 到 15 秒之间的时长，让您有空间在单次生成中讲述完整的故事、制作产品说明或制作完整的社交广告短片。

Better reference adherence. You can guide generation combining character, product, or style images, short motion clips (up to three seconds), and audio cues — and Omni 1.2 Flash holds onto those details from start to finish. Faces, garments, packaging typography, and brand colors stay consistent across camera angles, making it easy to turn existing product photography or character sheets into virtual try-on clips, catalog spins, and branded video ads.

更好的参考遵循能力。您可以结合角色、产品或风格图像、短动作片段（最长三秒）和音频提示来引导生成，而 Omni 1.2 Flash 会从始至终保持这些细节。面部、服装、包装排版和品牌颜色在不同摄像机角度下保持一致，从而可以轻松地将现有的产品摄影或角色表转换为虚拟试穿片段、目录旋转展示和品牌视频广告。

More consistent results. You can maintain stronger character, object, and scene consistency from the first to the last frame, with less visual drift or morphing across motion and camera transitions. Whether you’re interpolating between a first and last keyframe, or extending a clip to build a longer sequence, products, characters, props, and environments stay consistent from shot to shot.

更连贯的结果。您可以从第一帧到最后一帧保持更强的角色、物体和场景连贯性，在运动和摄像机转换过程中减少视觉漂移或变形。无论您是在首尾关键帧之间进行插值，还是扩展片段以构建更长的序列，产品、角色、道具和环境在镜头之间都能保持一致。

Easier editing in conversation. You can refine the same clip turn by turn — such as swapping a product or background, changing the lighting or weather, or switching the aspect ratio — instead of starting over from scratch. Multi-turn conversational editing works across full 15-second clips, making it easy to produce ad variants for different audiences and placements without re-briefing or re-generating.

对话式编辑更轻松。您可以逐轮优化同一个片段，例如更换产品或背景、改变光照或天气，或者切换长宽比，而无需从头开始。多轮对话编辑适用于完整的 15 秒片段，使您可以轻松地为不同的受众和投放位置制作广告变体，而无需重新简报或重新生成。

More natural speech. You can generate scenes with more fluid, natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning. This will show up whether you’re directing multi-character dialogue in Flow, creating video explainers in Gemini for business, or creating polished, pro videos with avatars, music and narration in Google Vids.

更自然的语音。您可以生成具有更流畅、听起来更自然的对话、更清晰的口型同步以及独特的多说话人条件的场景。无论您是在 Flow 中指导多角色对话、在 Gemini for business 中创建视频说明，还是在 Google Vids 中使用头像、音乐和旁白制作精美的专业视频，这些效果都会体现出来。

More controllable, cinematic look. You can direct complex, continuous camera movements like sweeping FPV flythroughs to dramatic zoom-outs and orbits with significantly fewer unwanted jump cuts, steadier scale, and a more polished, cinematic look. Guided by two architectural reference photos, Gemini Omni 1.2 Flash directs one continuous FPV drone flight across the piazza, through the bronze doors, and up through the Pantheon’s coffered dome to the oculus with zero jump.

更具可控性、电影感的视觉效果。您可以指导复杂的连续摄像机运动，例如扫视式的 FPV 飞行、戏剧性的缩放和轨道拍摄，同时显著减少不必要的跳剪，使比例更稳定，外观更精致、更具电影感。在两张建筑参考照片的引导下，Gemini Omni 1.2 Flash 指导了一次连续的 FPV 无人机飞行，穿过广场，穿过青铜门，并穿过万神殿的方格圆顶到达天窗，全程零跳剪。