跳到主内容
@wquguru
精选88Google Cloud AI 博客(RSS)产品发布/更新多源精选 ×6

Gemini Omni 1.2 Flash视频生成模型正式商用

Gemini Omni 1.2 Flash: Fast, cost-effective, and reliable video generation and editing now generally available

原文
发到 X
推荐理由

视频生成领域重磅更新,价格直降30%且时长突破至15秒,对做AIGC视频应用的同学极具参考价值,建议关注API接入成本变化。

Today, Gemini Omni 1.2 Flash is generally available on Google Cloud. Built for the everyday videos businesses make in volume — like product videos, virtual try-ons, and ads — this model is fast, cost-effective, and follows your image, video and audio references more closely than before.

今天,Gemini Omni 1.2 Flash 已在 Google Cloud 全面上线。该模型专为大规模制作的日常商业视频(如产品视频、虚拟试穿和广告)而设计,速度快、性价比高,且比以往更紧密地遵循您的图像、视频和音频参考。

Business users can create with it in Gemini for business and Google Vids, and developers can build with it via API.

企业用户可以在 Gemini for business 和 Google Vids 中使用它进行创作,开发者则可以通过 API 基于它进行构建。

Here's what's new:

以下是新增功能:

  • A lower price: $0.07 per second of 720p video, 30% less than Gemini Omni 1.1 Flash, with similar savings at other resolutions.
  • Longer clips: Generate and edit videos of up to 15 seconds, up from 10s.
  • More consistent results: stronger adherence to image and video references keeps products, characters, and brand details consistent from shot to shot.
  • Faster drafts, in higher resolution: create drafts at 360p or 720p, then upscale the best creations to 1080p or 4K.
  • More natural speech: You can generate scenes with more fluid, natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning.
  • Editing in conversation: refine the same clip, such as swapping a product, changing lighting, or changing camera angle, instead of starting over.
  • 更低的价格:720p 视频每秒 0.07 美元,比 Gemini Omni 1.1 Flash 低 30%,其他分辨率也有类似的节省。
  • 更长的片段:生成和编辑长达 15 秒的视频,较之前的 10 秒有所增加。
  • 结果更一致:更强的图像和视频参考遵循性,确保产品、角色和品牌细节在镜头之间保持一致。
  • 更高分辨率的快速草稿:以 360p 或 720p 创建草稿,然后将最佳作品放大至 1080p 或 4K。
  • 更自然的语音:您可以生成具有更流畅、自然对话的场景,口型同步更清晰,并支持区分多说话人条件。
  • 对话式编辑:对同一片段进行微调,例如替换产品、更改灯光或调整摄像机角度,而不是重新开始。

Note: Audio references are gated behind allowlisting.

注意:音频参考功能目前仅限白名单用户访问。

Gemini Omni 1.2 Flash is ready for production

Gemini Omni 1.2 Flash 已准备好投入生产环境

Gemini Omni 1.2 Flash is production-ready and backed by Google Cloud’s enterprise-grade infrastructure and security, offering Provisioned Throughput. Outputs carry an imperceptible SynthID watermark.

Gemini Omni 1.2 Flash 已具备生产就绪状态,并由 Google Cloud 的企业级基础设施和安全保障提供支持,提供预置吞吐量(Provisioned Throughput)。输出内容带有不可察觉的 SynthID 水印。

Video creation inside the tools people already use

在您已经使用的工具内进行视频创作

Design and creative platforms are building Gemini Omni 1.2 Flash directly into their products, so their users can create and edit videos where they already work. Here’s how customers are already using Gemini Omni 1.2 Flash:

设计和创意平台正在将 Gemini Omni 1.2 Flash 直接集成到其产品中,以便用户可以在他们熟悉的工作环境中创建和编辑视频。以下是客户如何使用 Gemini Omni 1.2 Flash 的案例:

“At Artlist, we’re focused on giving creators the control and flexibility to bring their ideas to life. Gemini Omni 1.2 Flash brings exciting capabilities in reference-based generation, video extension, and creative consistency, helping our customers move from experimentation to professional content production at scale.” – Roee Peled, CPTO, Artlist.

"在 Artlist,我们专注于赋予创作者控制权和灵活性,让他们能够将想法变为现实。Gemini Omni 1.2 Flash 带来了令人兴奋的功能,包括基于参考的生成、视频扩展和创意一致性,帮助我们的客户从实验阶段迈向大规模的专业内容制作。" —— Roee Peled,Artlist 首席产品技术官(CPTO)。

Artlist uses Gemini 1.2 Omni Flash to bring creative ideas to life

Artlist 使用 Gemini 1.2 Omni Flash 将创意想法变为现实

Artlist uses Gemini 1.2 Omni Flash to bring creative ideas to life

Artlist 使用 Gemini 1.2 Omni Flash 将创意想法变为现实

“Creative teams need models that they can rely on consistently. Gemini Omni 1.2 Flash edits exactly what you ask for, a colorway or a background, and leaves the product untouched, even from detailed images and finished video. Its video-to-video takes footage into entirely new styles.” – Andrew Taco Zhang, Product Marketing Manager, FLORA.

“创意团队需要能够始终信赖的模型。Gemini Omni 1.2 Flash 会精准修改你要求的部分,例如配色或背景,同时保持产品原样不动,即使面对细节丰富的图像和成品视频也是如此。其视频到视频的转换功能能将素材转化为全新的风格。”——FLORA 的产品营销经理 Andrew Taco Zhang

FLORA uses Gemini Omni 1.2 Flash to create new styles

FLORA 使用 Gemini Omni 1.2 Flash 创建新风格

FLORA uses Gemini Omni 1.2 Flash to create new styles

FLORA 使用 Gemini Omni 1.2 Flash 创建新风格

“We ran Gemini Omni 1.2 Flash through our evals at invideo. Honestly, it's really good. It sticks to the prompt, and the physics and sound feel real. If you need fast video at scale, it's one of the best we've tested. And 15 seconds means a full scene in one go.” – Shivam Rastogi, VP of Engineering, invideo.

“我们在 invideo 对 Gemini Omni 1.2 Flash 进行了评估测试。老实说,它非常出色。它能严格遵循提示词,物理效果和音效都显得真实自然。如果你需要大规模快速生成视频,这是我们测试过的最佳选择之一。15 秒的时长意味着可以一次性完成整个场景的制作。”——invideo 工程副总裁 Shivam Rastogi

invideo uses Gemini Omni 1.2 Flash to create full scenes in one prompt

invideo 使用 Gemini Omni 1.2 Flash 通过单个提示词创建完整场景

invideo uses Gemini Omni 1.2 Flash to create full scenes in one prompt

invideo 使用 Gemini Omni 1.2 Flash 通过单个提示词创建完整场景

“We’re really impressed by how fast and accurate this new model is. The outputs retain an amazing level of detail, and the model does a great job of making only the changes we ask for while keeping everything else consistent. We’re excited to use it for character and scene replacements, as well as other creative workflows.” – Numan Khan, Creative Specialist, Krea.

“我们对这款新模型的快速响应和高准确性印象深刻。输出结果保留了惊人的细节水平,模型在仅执行我们要求的更改的同时,能很好地保持其他所有内容的一致性。我们很期待将其用于角色和场景替换,以及其他创意工作流程。”——Krea 创意专家 Numan Khan

Krea uses Gemini Omni 1.2 Flash for their creative workflows, from character to scene replacements

Krea 使用 Gemini Omni 1.2 Flash 进行从角色到场景替换的创意工作流程

Krea uses Gemini Omni 1.2 Flash for their creative workflows, from character to scene replacements

Krea 使用 Gemini Omni 1.2 Flash 进行从角色到场景替换的创意工作流程

"Gemini Omni 1.2 fits the way our teams work. Draft mode lets us iterate concepts in minutes, then render in 4K for TV-ready AI dramas. Text stays crisp across frames, characters look and sound real, and the speed keeps production moving. Now that it is generally available, we can bring this quality to over 100M Picsart creators." – Narek Hayrapetyan, Head of Product and Partnerships, Picsart.

“Gemini Omni 1.2 非常契合我们团队的工作方式。草稿模式让我们能够在几分钟内迭代概念,然后以 4K 分辨率渲染,制作出适合电视播出的 AI 剧集。文字在各帧中保持清晰锐利,角色看起来和听起来都很真实,而且速度保证了生产流程的顺畅推进。现在它已全面开放,我们可以将这种品质带给超过 1 亿 Picsart 创作者。”——Picsart 产品与合作负责人 Narek Hayrapetyan

Picsart uses Gemini 1.2 Flash to iterate concepts in minutes

Picsart 使用 Gemini 1.2 Flash 在几分钟内迭代概念

Picsart uses Gemini 1.2 Flash to iterate concepts in minutes

Picsart 使用 Gemini 1.2 Flash 在几分钟内迭代概念

Runway empowers creatives with advanced AI video tools to produce high-quality content. For organizations, Runway’s enterprise solutions deliver robust collaborative tools to scale professional production. Here is what they created with Gemini Omni 1.2 Flash.

Runway 通过先进的 AI 视频工具赋能创意人员,以制作高质量内容。对于企业组织而言,Runway 的企业解决方案提供了强大的协作工具,以实现专业制作的规模化扩展。以下是他们使用 Gemini Omni 1.2 Flash 创作的内容。

Runway uses Gemini Omni 1.2 Flash to produce and scale high-quality content

Runway 使用 Gemini Omni 1.2 Flash 生产和规模化高质量内容

Runway uses Gemini Omni 1.2 Flash to produce and scale high-quality content

Runway 使用 Gemini Omni 1.2 Flash 生产和规模化高质量内容

Product and listing videos at catalog scale

目录规模的产品和展示视频

Retailers and marketplaces use Gemini Omni to turn the photos they already have into short product spins, lifestyle clips, try-on videos, and video ads.

零售商和电商平台使用 Gemini Omni 将他们已有的照片转化为简短的产品旋转展示、生活场景短片、试穿视频以及视频广告。

“Photoroom turns product photos into video ads that sell in minutes. We chose Gemini Omni Flash to power our Video Ad Maker and Product Animator because it balances quality, speed and cost. Version 1.2 brings 15-second videos, a top user request. With general availability and SLAs, we can rely on it in production for our sellers and enterprise customers.” - Matt Rouif, CEO and Co-founder, Photoroom.

“Photoroom 能在几分钟内将产品照片转化为促进销售的视频广告。我们选择 Gemini Omni Flash 来驱动我们的 Video Ad Maker 和 Product Animator,因为它在质量、速度和成本之间取得了平衡。1.2 版本带来了用户呼声最高的 15 秒视频功能。随着通用可用性(GA)和服务等级协议(SLA)的推出,我们可以将其可靠地用于面向卖家和企业客户的正式生产环境。” —— Matt Rouif,Photoroom 首席执行官兼联合创始人。

Photoroom uses Gemini Omni 1.2 Flash to power their Video Ad Maker and Product Animator

Photoroom 使用 Gemini Omni 1.2 Flash 来驱动其 Video Ad Maker 和 Product Animator

Photoroom uses Gemini Omni 1.2 Flash to power their Video Ad Maker and Product Animator

Photoroom 使用 Gemini Omni 1.2 Flash 来驱动其 Video Ad Maker 和 Product Animator

“QuickFrame AI helps marketers and business owners create, edit, and launch professional-quality ads for CTV and social in minutes. With Gemini Omni 1.2 Flash now supporting 15-second video generations at 1080p, users can create a complete CTV ad in a single generation, making TV ad creation simpler for businesses of all sizes.” - Richard Girges, Chief Technology Officer, QuickFrame AI.

“QuickFrame AI 帮助营销人员和企业主在几分钟内创建、编辑并发布适用于联网电视(CTV)和社交媒体的专业级广告。随着 Gemini Omni 1.2 Flash 现在支持以 1080p 分辨率生成 15 秒视频,用户可以在单次生成中完成整个 CTV 广告的制作,从而让各种规模的企业制作电视广告变得更加简单。” —— Richard Girges,QuickFrame AI 首席技术官。

QuickFrame AI uses Gemini Omni 1.2 Flash to create complete CTV ads in a single generation

QuickFrame AI 使用 Gemini Omni 1.2 Flash 在一次生成中创建完整的 CTV 广告

QuickFrame AI uses Gemini Omni 1.2 Flash to create complete CTV ads in a single generation

QuickFrame AI 使用 Gemini Omni 1.2 Flash 在一次生成中创建完整的 CTV 广告

Create in Gemini for business, Google Vids and build with the API

在 Gemini for Business、Google Vids 中创作,并通过 API 进行构建

Coming soon to Gemini, business users will be able to create a short video from a prompt or a product photo, right in the chat. In Google Vids, teams can combine generated clips with avatars, music and voiceover to create product explainers, teasers, social posts and sales pitches. Businesses can also embed the capabilities of Gemini Omni 1.2 Flash into their applications and agents via the API.

即将登陆 Gemini:企业用户将能够在聊天界面中,通过提示词或产品照片直接生成短视频。在 Google Vids 中,团队可以将生成的片段与虚拟形象、音乐和旁白相结合,制作产品介绍视频、预告片、社交媒体帖子和销售话术视频。企业还可以通过 API 将 Gemini Omni 1.2 Flash 的能力嵌入到他们的应用程序和智能体中。

Get started with Gemini Omni

开始使用 Gemini Omni

We'll keep improving Gemini Omni based on your feedback, so tell us what you build.

我们将根据您的反馈持续改进 Gemini Omni,因此请告诉我们您利用它构建了什么。

  • For business users: Try it in Google Vids; coming soon to Gemini for business
  • For developers: Try it in the Google Cloud console, build with the API, and see the pricing
  • 面向企业用户:可在 Google Vids 中试用;即将登陆 Gemini for Business
  • 面向开发者:在 Google Cloud 控制台中试用,通过 API 进行构建,并查看定价信息

更进一步:量化金融体系

看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力

进入量化体系 →