Google DeepMind

Model Profile

Gemini Omni 1.1 Flash

Google DeepMindAI Video Generation

Google's fast multimodal video model for text and image generation, first-and-last-frame interpolation, native audio, extension, and conversational editing up to 4K.

Provider

Google DeepMind

Workflow

AI Video Generation

Key features

4

Example Videos for Gemini Omni 1.1 Flash

Media below is reused from the Unify landing page model viewer so each model page has a concrete example section instead of text alone.

Example video

Stunning quality

Example video

Movie-like shots

Example video

Ultra realistic

About Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is Google DeepMind's multimodal video-generation and editing model, available on Unify through the Gemini Interactions API. It creates video with synchronized dialogue, music, and effects from text or images; interpolates between first and last frames; uses image and short-video references; edits videos conversationally; and extends generated clips in 3-to-10-second steps up to 40 seconds. Output ranges from economical 360p drafts to upscaled 1080p and 4K delivery.

Key Features

01

360p to 4K output

02

Text, image & video inputs

03

Conversational editing and extension

04

Native synchronized audio

Best For

01

Fast 360p concept iteration

02

Native-audio product and social clips

03

First-and-last-frame transitions

04

Conversational editing and scene extension

Technical Specifications

ProviderGoogle DeepMind
Model IDgemini-omni-1.1-flash
AvailabilityPreview; live on Unify
Generation length3–10 seconds per request
ExtensionUp to 40 seconds total
Output360p, 720p, 1080p, or 4K; 16:9 or 9:16
AudioSynchronized speech, music, ambience, and effects
PricingResolution-based credits with a quote before generation

Pros

Native multimodal video and audio

Low-cost 360p draft tier

Conversational edits and multi-turn extension

First/last frames plus image and video references

Cons

Preview availability and fixed quota

No free tier or batch discount

Uploaded-video editing is region-restricted

4K output costs roughly nine times as much per second as 360p

How to Use Gemini Omni 1.1 Flash

01

Sign Up Free

Create your Unify account in seconds. No credit card required.

02

Select Gemini Omni 1.1 Flash

Choose Gemini Omni 1.1 Flash from the model selector in the video interface.

03

Start Creating

Enter your prompt and let Gemini Omni 1.1 Flash generate amazing results.

Other Video Models on Unify

Popular Use Cases

Frequently Asked Questions About Gemini Omni 1.1 Flash

What is Gemini Omni 1.1 Flash?+
Gemini Omni 1.1 Flash is Google's native multimodal video model for text-to-video, image-to-video, frame interpolation, reference-driven generation, conversational editing, and video extension with synchronized audio.
Which resolutions does Gemini Omni 1.1 Flash support?+
It supports 360p drafts, standard 720p, upscaled 1080p, and upscaled 4K output in 16:9 or 9:16.
How is Gemini Omni 1.1 Flash priced on Unify?+
Credits scale with video duration and resolution. Unify calculates the published video-token rate with its 20% gross margin, then shows the credit quote before generation. Image and uploaded-video inputs are included when applicable.
Can Gemini Omni 1.1 Flash edit an existing video?+
Yes. You can upload a supported video or select an earlier Omni result and describe the change conversationally. Uploaded-video editing is restricted by Google in the EEA, Switzerland, and the United Kingdom.
Can it extend videos?+
Yes. Omni can append a 3-to-10-second continuation and can extend generated clips across turns up to 40 seconds total. It cannot prepend footage or insert an extension into the middle.
Does Gemini Omni generate sound?+
Yes. Prompt for dialogue, music, ambience, and sound effects alongside the visuals. Voice editing is not currently supported.

Ready to Try Gemini Omni 1.1 Flash?

Join thousands of creators using Unify to access the best AI models in one place.