Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is Google's multimodal video model. On GoEnhance it turns a prompt, a photo, a first and last frame, or up to 10 reference images into a 3 to 15 second clip with sound built in: dialogue, music and effects come from your prompt. Draft at 360p, then render at 720p, 1080p or 4K, in 16:9 or 9:16.

Café Order

Rainy Bus Stop

Kneading Lesson

Tide Pool Find

Gemini Omni 1.2 Flash

Prompt

Starting image (optional)

Add a photo to animate it, or skip this and generate from your prompt.

Example prompts

By uploading a file, you agree to GoEnhance's Terms of Use and Privacy Policy

What Gemini Omni 1.2 Flash Does

Sound Comes With Every Clip

Write the line a character says, the music or the background noise in your prompt, and the clip comes back with that audio. Audio is always on, with nothing extra to switch on or pay for.

Five Ways to Start

Text to video, image to video, first and last frame, video extension and reference to video all run on the same model on GoEnhance, so one project can keep one look.

Up to 10 Reference Images

Add characters, products or places as references. They guide who and what appears in the video without being used as exact frames.

360p Drafts, 4K Finals

Test a prompt at 360p for 4 tokens per second, then render the version you like at 720p, 1080p or 4K. 1080p and 4K are upscaled by the model.

Frame-to-Frame Transitions

Give a first and a last frame and the model fills in the motion between them, in clips of up to 10 seconds: before-and-after shots, reveals and day-to-night changes.

Gemini Omni 1.2 Flash vs Kling 4.0 Flash vs Kling 4.0 on GoEnhance

	Gemini Omni 1.2 Flash	Kling 4.0 Flash	Kling 4.0
Made by	Google	Kuaishou (Kling)	Kuaishou (Kling)
Ways to start on GoEnhance	Text, image, first & last frame, extend, up to 10 reference images	Text, image (first frame), extend, up to 10 reference images	Text, image, first & last frame, extend
Length	3–15 s (up to 10 s with a last frame)	3–20 s	3–30 s
Resolution	360p, 720p, 1080p, 4K	720p	720p, 1080p
Aspect ratios	16:9, 9:16	16:9, 9:16, 1:1, 21:9 (text to video)	16:9, 9:16, 1:1, 21:9 (text to video)
Audio	Always on	Always on	Always on
Tokens per second	4 / 11 / 17 / 34 (360p to 4K)	16	29 / 44 (720p / 1080p)

How to Use Gemini Omni 1.2 Flash on GoEnhance

Pick the model and a starting point

Open the AI video generator and select Gemini Omni 1.2 Flash. Add one photo for image to video, two photos for a first and last frame, or up to 10 reference images.

Write the scene and the sound

Describe the action, the camera and what we should hear, with any spoken line in quotes. A prompt is required in every mode.

Set length, resolution and ratio

Choose 3 to 15 seconds, 360p to 4K, and 16:9 or 9:16. The token cost is shown before you generate.

Generate and download

Your clip arrives with audio. Download it, or extend it with another shot.

Try Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash FAQ

What is Gemini Omni 1.2 Flash?

It is Google's multimodal video model. It makes 3 to 15 second clips with native audio from text, a photo, a first and last frame, or reference images.

Does every video have sound?

Yes. Audio is generated with every clip and cannot be turned off. Describe the dialogue, music or sound effects you want in the prompt.

How many tokens does it use on GoEnhance?

It is billed per second: 4 tokens at 360p, 11 at 720p, 17 at 1080p and 34 at 4K. A 10-second clip at 720p uses 110 tokens. Gemini Omni 1.2 Flash is available to members.

How long can a video be?

3 to 15 seconds. With a first and last frame, the limit is 10 seconds.

Can I combine reference images with a first frame?

No. In one generation, use either a first (and last) frame or reference images.

How is it different from Gemini Omni Flash?

Gemini Omni 1.2 Flash is a separate, newer model. On GoEnhance it supports 3 to 15 second clips, 360p to 4K, first and last frames and up to 10 reference images.

Were the sample clips on this page made with Gemini Omni 1.2 Flash?

No. The clips in the console above were made with Wan 3.0 on GoEnhance to show the prompts. Run the same prompts with Gemini Omni 1.2 Flash to see its own results.

Explore More Video Models

Gemini Omni Flash

Kling 4.0 Flash

Kling 4.0

Veo 3

Wan 3.0

Make Videos with Sound Using Gemini Omni 1.2 Flash

Start from a prompt, a photo or your references and get a 3 to 15 second clip with audio, from 360p drafts to 4K.

Start Creating