Gemini Omni 1.2 Flash

Create short films with native sound. Start from a prompt, guide the scene with references, and choose 3–15 seconds in landscape or portrait.

Video

Opens Clico Web in a new tab. Review your prompt and settings before sending.

Through the Pantheon, a frame from Google’s Gemini Omni launch demonstration

Through the Pantheon

A continuous camera move crosses the piazza, enters the building and rises toward the open dome.

A starting prompt to adapt

One continuous cinematic drone shot at golden hour. Travel across a Roman piazza into the Pantheon, glide beneath the coffered dome, then rise toward the open oculus. Warm stone, long shadows and a steady sense of scale. Natural city ambience and a gentle musical swell.

Google DeepMind launch example, shown as an excerpt. View the original demonstration. The suggested prompt prepares a new draft; it is not the original Google prompt.

An island revealed, a frame from Google’s Gemini Omni launch demonstration

An island revealed

An intimate shoreline scene opens into a wide aerial reveal.

A starting prompt to adapt

Begin with a close-up of a castaway kneeling beside driftwood on a tropical beach. In one continuous shot, pull smoothly back and upward until the turquoise bay and green island fill the frame. Keep the person in place as the landscape opens up. Ocean surf and wind.

Google DeepMind launch example, shown as an excerpt. View the original demonstration. The suggested prompt prepares a new draft; it is not the original Google prompt.

Inside a living hive, a frame from Google’s Gemini Omni launch demonstration

Inside a living hive

Macro shots, tracked labels and changes of scale form a short visual explainer.

A starting prompt to adapt

Create a 15-second cinematic macro explainer inside a golden honeycomb. Move from worker bees to the queen, then to eggs and larvae, ending with nectar becoming honey. Use four deliberate shots with clean match cuts and small legible labels. Warm light, detailed textures, quiet hive ambience.

Google DeepMind launch example, shown as an excerpt. View the original demonstration. The suggested prompt prepares a new draft; it is not the original Google prompt.

From your words to a moving scene.

Describe the moment, choose the shot and bring it to life in Clico.

Direct the whole moment

Subject
The person, place or product at the heart of the scene.
Camera
A slow push, an orbit or a sweeping reveal. Give the movement a clear destination.
Sound
The ambience, dialogue or music that makes the moment feel complete.
Start your scene

  1. Describe the scene

    Name the subject, one action and the sound. Start from words or add your own reference images.

  2. Choose the shot

    Set the duration, resolution and aspect ratio. Describe the camera movement, or ask for a locked-off shot.

  3. Review in Clico

    Continue to Clico Web to review and send your draft. Watch the movement and listen to the sound before your next take.

Create with Gemini Omni →

Choose the shot you want.

Compare the duration, framing and reference controls available in Clico.

Gemini Omni 1.2 Flash offers automatic native sound and output from 360p to 4K for Pro and Max. Use up to five reference images or one video reference in Clico. Last-frame interpolation supports 3–10 seconds.

Settings available in Clico, reviewed November 6, 2026
ModelDurationResolutionImage inputsAudio and framing
Gemini Omni 1.2 Flash3 to 15 seconds360p, 720p, 1080p, 4KUp to 5 references
First frame, Last frame		Automatic native sound
16:9, 9:16
Seedance 2.54 to 30 seconds480p, 720pUp to 5 references
First frame, Last frame		Optional generated audio
16:9, 4:3, 1:1, 3:4, 9:16, 21:9
Veo 3.1 Fast4, 6, 8 seconds720p, 1080p, 4KUp to 5 references
First frame, Last frame		Optional generated audio
16:9, 9:16

These are Clico controls. A provider may expose additional features on its own platform. Availability depends on your account and the generation provider.

Plan your next clip.

Choose a resolution and duration to estimate the generation charge.

ResolutionUSD per second8-second estimate
360p$0.030123625 credits
720p$0.090355273 credits
1080p$0.1355328109 credits
4K$0.2710656217 credits
73 credits

One credit represents $0.01. Each clip’s charge is rounded up to a whole credit. These rates include Clico’s 30% markup; chat and other activity use additional credits.

Explore Pro and Max plans →

Gemini Omni questions.

Who can use Gemini Omni 1.2 Flash?

Gemini Omni 1.2 Flash is available on Clico Pro and Max with enough credits for the selected clip.

Can I start from an image or a video?

Yes. Use up to five ordinary reference images or one video reference in Clico. First and last frames are separate boundary controls. Choose video references or boundary frames for a request, rather than mixing both.

Can I generate a 15-second clip?

New clips can be 3–15 seconds. When you supply a last frame for interpolation, choose 3–10 seconds. Describe one clear action and where the shot should finish.

Does the model generate sound?

Yes. Native sound is automatic. Describe dialogue, ambience or sound effects in your prompt. Clico does not offer a separate silent-output switch for this model.

Does trying a prompt start a paid generation?

No. The prompt button fills the composer. Continue to Clico Web, sign in if needed, review your settings and explicitly send the request to start generation.

Explore more AI tools.

Keep creating with the model and workflow that fit your idea.

Create with Gemini Omni