Google Vids 中的 Gemini Omni 和个人虚拟形象让视频创作比以往任何时候都更轻松。现在，你可以用日常语言生成和编辑高质量片段，并创建一个专属数字虚拟形象来出演你的视频。
Justin Luk
产品经理
今天，我们为 Google Vids 推出两项新更新，让创建、编辑和个性化你的视频比以往任何时候都更轻松：Gemini Omni 和个人虚拟形象。Gemini Omni 免去了编辑过程中的繁琐工作，让生成和优化高质量片段就像写一句简单的提示词一样容易。而借助个人虚拟形象，你有了一种全新的方式出演视频，无需架设摄像机。
下面来看看这些新工具如何改变视频创作。
从文本和图像生成视频
在过去一年里，你在 Google Vids 中创作了数百万个视频，用来分享你的故事、让你的想法变为现实。今年 2 月，我们向所有用户推出了 Veo 3.1，让这一过程更加简单，帮助每个人都能在 Vids 中生成视频。
现在，我们将 Gemini Omni 引入 Vids，你只需描述自己想要看到的内容，就能创建和编辑高质量视频。从一句自然语言的简单文本提示词开始，再添加图像参考——比如一张照片或一张粗略草图——来补充更多细节。Omni 会混合你的各项输入，生成符合你构想的视频。
对话即可编辑，逐步完成
想要让视频完全达到理想效果，往往需要在初稿之后做几次调整——而现在，做这些编辑就像描述你想看到的效果一样简单。无论你是在完善用 Omni 生成的视频，还是用手机拍摄的片段，都可以用日常语言提示 Vids 更换背景、修正光线或添加特效。
由于 Omni 支持逐步编辑，你现在可以对视频进行修改，而无需从头开始。
瞬间出镜，成为视频主角
想发送一条简短的视频更新或个性化的问候，却没时间打理好上镜状态？借助全新的个人虚拟形象，你可以创建一个外观和声音都像你的数字分身。只需上传一张自拍和一段简短录音。之后，输入你想说的话，你的虚拟形象就会替你传达——无需录制。
Gemini Omni 和个人虚拟形象已在 Google Vids 中面向 Google AI Pro 和 Ultra 订阅用户以及 Google Workspace 企业客户开放。个人虚拟形象目前仅限某些地区年满 18 岁的用户使用。个人虚拟形象与用户的 Google 账号绑定，且仅限于账号持有人本人的形象。
透明地创建与分享
我们希望你能放心地分享自己创作的内容。为确保内容透明，每一段生成的视频片段都包含不可见的 SynthID 数字水印。这让人们能够验证视频是由 AI 创建的，因此你可以尽情探索自己的创造力，并负责任地分享你的 AI 视频。
快来 Google Vids 看看你能用 Gemini Omni 和个人虚拟形象创作出什么吧。
Gemini Omni and personal avatars in Google Vids make video creation easier than ever. Now you can generate and edit high-quality clips using everyday language, and create a custom digital avatar to star in your videos.
Justin Luk
Product Manager
Today, we’re rolling out two new updates to Google Vids to make it easier than ever to create, edit and personalize your videos: Gemini Omni and personal avatars. Gemini Omni takes the hard work out of the editing process, so generating and refining high-quality clips is as easy as writing a simple prompt. And with personal avatars, you have an entirely new way to star in videos without setting up a camera.
Here’s a look at how these new tools transform video creation.
Generate videos from text and images
In the past year, you’ve created millions of videos in Google Vids to share your stories and bring your ideas to life. In February, we made the process simpler by rolling out Veo 3.1 to all users, helping everyone generate videos within Vids.
Now, we’re bringing Gemini Omni to Vids, so you can create and edit high-quality videos just by describing what you want to see. Start with a simple text prompt in natural language, and add image references — like a photo or a rough sketch — for more detail. Omni mixes your inputs to generate a video that matches your vision.
Chat to edit, step-by-step
Getting a video exactly right often requires a few tweaks after that first draft — and making those edits is now as easy as describing what you want to see. Whether you're refining a video you generated with Omni or a clip you shot on your phone, you can use everyday language to prompt Vids to swap backgrounds, fix lighting or add effects.
Because Omni supports step-by-step edits, you can now make changes to your videos without starting from scratch.
Star in videos, instantly
Want to send a quick video update or personalized shout-out, but don't have time to get camera-ready? With new personal avatars, you can create a digital avatar that looks and sounds like you. Just upload a selfie and a short voice recording. From there, type what you want to say and your avatar will deliver the message — no recording required.
Gemini Omni and personal avatars are available in Google Vids for Google AI Pro and Ultra subscribers and Google Workspace business customers. Access to personal avatars is currently limited to users in certain regions who are 18 or older. Personal avatars are linked to a user’s Google Account and are restricted to the account holder’s likeness.
Create and share with transparency
We want you to feel confident sharing what you create. To ensure content transparency, every generated clip includes an invisible SynthID digital watermark. This allows people to verify that a video was created with AI, so you can explore your creativity and share your AI videos responsibly.
Come see what you can create with Gemini Omni and personal avatars in Google Vids.