惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

C
Check Point Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园 - 聂微东
月光博客
月光博客
博客园 - 司徒正美
爱范儿
爱范儿
aimingoo的专栏
aimingoo的专栏
量子位
Recent Announcements
Recent Announcements
V
V2EX
P
Proofpoint News Feed
小众软件
小众软件
云风的 BLOG
云风的 BLOG
腾讯CDC
宝玉的分享
宝玉的分享
Microsoft Azure Blog
Microsoft Azure Blog
大猫的无限游戏
大猫的无限游戏
Vercel News
Vercel News
The GitHub Blog
The GitHub Blog
A
About on SuperTechFans
B
Blog
博客园_首页
GbyAI
GbyAI
博客园 - Franky

Google DeepMind

Recreating a 70-year love story frame by frame AlphaGenome Atlas: a high-resolution map of human DNA Backing 16 green AI projects in Asia-Pacific Introducing WeatherNext 3, our most advanced and accurate global weather AI model The latest AI news we announced in August 2026 Ask a Scientist: How do researchers use AI to predict a cyclone? What does “full-stack” AI actually mean? Omni experts share what excites them most about the model. AMIE, our research medical AI system, demonstrates real-time clinical video consultation capabilities in a first-of-its-kind study. Our WeatherNext 2 AI model demonstrated a massive leap forward in predicting cyclones. The latest AI news we announced in July 2026 Introducing Gemini Robotics ER 2 We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control. Reconstructing Pelé’s “lost” goal We're rolling out AlphaEvolve widely to solve Google Cloud customers' hardest problems. The latest AI news we announced in June 2026 Google DeepMind and A24 announce first-of-its-kind research partnership New research shows how AMIE, our medical AI, could help manage health conditions. The latest AI news we announced in May 2026 9 demos of Gemini Omni and Gemini 3.5 in action Running Guide agent: A step towards running unbounded Making it easier to understand how content was created and edited Simulate real-world places with Project Genie and Street View Gemini for Science: AI experiments and tools for a new era of discovery We’re launching the Google DeepMind Accelerator program in Asia Pacific to tackle environmental risks. Find out how AlphaEvolve has gone from research to solving real-life problems. Join the new AI Agents Vibe Coding Course from Google and Kaggle Gemini Robotics ER-1.6 enhances reasoning to help robots navigate real-world tasks. The latest AI news we announced in March 2026 Measuring progress toward AGI: A cognitive framework
See what 5 builders are making with Gemini Omni
Lindsey Lanquist · 2026-08-07 · via Google DeepMind

Gemini Omni makes creating videos as easy as having a conversation. Here are some of the coolest things people and companies are building with it.



Gemini Omni images

Your browser does not support the audio element.

Listen to article

[[duration]] minutes

This content is generated by Google AI. Generative AI is experimental

At this year’s I/O, we introduced Gemini Omni Flash, our first model in the new Omni family. Omni makes creating and editing videos as easy as having a conversation. You can generate high-quality videos from text, image, video, or audio references, and even edit your own videos. And since Omni combines an intuitive understanding of physics with Gemini’s real-world knowledge, it creates more realistic outputs.

We recently gave developers access to Omni, and builders have already used it for a range of projects. Here are some of the demos that caught our eye.

Switch angles and perspectives.

Omni makes editing videos incredibly easy. You can change camera angles, switch environments, and apply cinematic zooms — all without losing the thread of your original scene.

Builder Leon Lin (@LexnLin on X) took full advantage of this capability, capturing a woman standing in the middle of a city from about 20 different perspectives. You see her from every angle imaginable: up close and far away, head on and in profile, from above, and from below. Some shots zoom in, while others hold still. And the background shifts: She stands on sidewalks, crosswalks, and city streets, surrounded by pedestrians, cars, trams, and a range of different buildings.

Transform the world around you.

Omni lets you change what’s happening in a video and create something you never could have filmed yourself. You can edit the action or swap in different objects, and Omni will still maintain a coherent, cohesive scene.

Take this video from builder Carlos Santana (@DotCSV on X), for example. He changes an outdoor scene using only his voice, switching the lighting from day to night, adding cloudy skies and rainy sounds, turning the leaves orange, and covering the ground in snow.

Animate everyday objects.

With Omni in Google Flow, you can turn sketches into realistic videos, using doodles to guide how individual elements move. And you can decide whether these hand-drawn elements become part of your final product.

Builder Pan (@sebatheepan on X), for instance, uses doodles to playfully transform everyday objects. A lemon becomes a submarine bobbing in the ocean. A cup of espresso is now a hot air balloon transporting someone through the sky. A pair of hot peppers form a sleeping dragon that breathes fire when startled. A match is recast as a rocket ship. And scissors turn into a scary shark looking for a snack.

Play with different styles or visual effects.

Curious what your video would look like with a completely different aesthetic? With Omni, you can change styles and apply effects to create something that matches your vision. Define the look you want by inputting references, or just describe what you’re looking for in natural language. Omni blends that together to create a cohesive clip.

Builder Jerrod Lew (@jerrod_lew on X) put this to the test with Omni in Google Flow, rendering a video of a woman walking down the street in four different animation styles. The original clip fluidly shifts from live-action to anime to claymation and more, never interrupting the woman’s natural forward progression.

Bring ideas to life.

The team at Hyperagent (@hyperagentapp on X) used Omni to visualize three different concepts with video. They layered landscaping into a video of an empty park to create a before-and-after design proposal. They personified data with an animated professor who explains business dashboards. And they gamified a to-do list with a video showing a character clearing tasks.

Omni blends knowledge with creativity, letting you create scenes that follow real-world logic. Try it in the Gemini app, Google Flow, Google AI Studio, the Gemini API, or the Gemini Enterprise Agent Platform.

Get the latest news from Google in your inbox

Sign up for our newsletters with product updates, event information, special offers, and more.

Your information will be used in accordance with Google's privacy policy. You may opt out at any time.