New to AI? You only need three labels to begin: the company makes the technology, the model is the engine, and the app is what you open. A method is a recipe developers use to build or teach AI.

Made byGoogle DeepMind
What kind of thing?Creative video model
Can I use it directly?Google lists Gemini and Flow as places to try it. Access depends on the service and plan.
An open notebook with a speech bubble, paper boat and bright light bulb representing words and ideas.
A question, a picture or an idea can be a starting point. The model’s job depends on what it was built to do.

See the idea in three steps

Start withA scene you describe
AI helps withCreate or edit video
You getA scene to review

A simple illustration of the idea. Results depend on the model, training and app.

A familiar way to picture it

An everyday analogyImagine describing a scene to a creative helper that can turn instructions and reference material into video.

An analogy helps you understand the main idea. It is not a description of every technical detail.

A simple Gemini Omni example

You describe a short scene or provide a picture to help create a video.

1

You provide an instruction and, when supported, reference material.

2

The video model creates or edits a scene.

3

You review the result and refine the instruction.

Is Gemini Omni the same as Gemini Nano?

No. Omni is associated with creative video generation and editing. Nano is designed for on-device AI tasks. Sharing the Gemini family name does not make their jobs identical.

Where can I try it or learn more?

Google lists Gemini and Flow as places to try it. Access depends on the service and plan.

Official page and tools ↗

A maker’s page or research page may explain the technology rather than provide a chat box. Available models, features and access can change.

A small activity for you

Write a clear scene description: “A paper boat floats across a puddle in soft morning light.” Add what should move and how long the shot should feel. This is planning practice; generation happens in the external tool.

You do not need to memorise model sizes or write a program to understand this lesson. First explain the idea in your own words. If you want to build an app later, the official resources are your next step.

Common beginner questions

Is Gemini Omni the same as Gemini Nano?

No. Omni is associated with creative video generation and editing. Nano is designed for on-device AI tasks. Sharing the Gemini family name does not make their jobs identical.

Who made Gemini Omni?

Google DeepMind. Google lists Gemini and Flow as places to try it. Access depends on the service and plan.

How can I start learning this topic?

Write a clear scene description: “A paper boat floats across a puddle in soft morning light.” Add what should move and how long the shot should feel. This is planning practice; generation happens in the external tool.

Keep learning

These related lessons help you compare the names without getting lost in technical details.

What Is Gemini Nano? Google’s On-Device AI Explained →What Is a GAN? Generative Adversarial Networks Made Simple →

See all 20 AI names and the seven-day learning plan →

Sources and review date

Reviewed 3 November 2026. Examples and analogies are written for beginners. Product facts are linked to the maker, original project or research below.