What Gemini Omni Does
Gemini Omni behaves like a video creation model that can understand multiple kinds of references, preserving relationships, rhythm, and action intent across the output.
Multi-Reference Fusion
It combines image, video, audio, and text references so the output can respond to several inputs at once.
Video Editing And Rewriting
It can keep motion or scene structure while changing materials, characters, environments, camera angles, and visual style.
Rhythm And Story Control
It can organize motion around music, dialogue, word timing, or a storyboard sequence.
Featured Omni Cases
Start with three examples that best show multi-input fusion, storyboard control, and semantic editing.
Multi Input4 inputs
Birds Shape With Audio
The birds from <video> loosely form the imperfect shape of a bird based on <image>. They move to the music from <audio> and dissipate as they fly
Storyboard2 inputs
Storyboard Show Me
Show me in this story. Follow the story exactly in order starting top left. Entire story in 10 seconds. Cinematic
Semantic Swap1 input
Spaceships White Origami
Change the ships to be made from white origami paper.
Get Inspired by Gemini Omni
These examples prioritize samples where public input assets are exposed, making the Omni workflow easier to inspect.
001Mirror Transform
Mirror Liquid Metal
When the person touches the mirror, make the mirror ripple beautifully like liquid, and the person's arm...
Gemini OmniNo exposed inputs
002Mirror Transform
Mirror Line Art
When the person touches the mirror, the person transforms into a detailed monochrome line art drawing
Gemini OmniNo exposed inputs
003Mirror Transform
Mirror Puppet
When the person touches the mirror, the person suddenly transforms into a cute felted stuffed puppet...
Gemini OmniNo exposed inputs
004Mirror Transform
Mirror Holograph
When the person touches the mirror, the person instantly transform into a vintage monochrome transparent...
Gemini OmniNo exposed inputs
005Mirror Transform
Mirror Voxel World
When the person touches the mirror, the entire environment turns into 3d voxel art
Gemini OmniNo exposed inputs
006Optical Effect
Handhole Super Zoom
Make it look like the weird shape of my hand hole super zooms and magnifies the ground it's looking at...
Gemini OmniNo exposed inputs
007Audio Trigger
Animal Toy Sound
When the finger in <video> touches the animal toy play the sound the animal makes
Gemini OmniNo exposed inputs
008Audio Sync
Apartments Lights Sync
The lights of the apartments start turning on in sync with the music.
Gemini OmniNo exposed inputs
009Camera And Scene Edit
Violinist Input
A video of a violinist playing a song.
Google BlogNo exposed inputs
010Camera And Scene Edit
Violinist Transport Environment
Transport the violinist to the image environment
Gemini Omni1 input
011Camera And Scene Edit
Violinist Invisible Violin
Make the violin invisible
Gemini Omni1 input
012Camera And Scene Edit
Violinist Over Shoulder
Change the camera angle to be over the violinist’s shoulder.
Gemini Omni1 input
013Sequence
Marble Chain Reaction
A marble rolling fast on a chain reaction style track, continuous smooth shot
Gemini OmniNo exposed inputs
014Sequence
Alphabet Items Sequence
The video shows items of the alphabet. An unusual item starting with each letter is shown sitting on a...
Google BlogNo exposed inputs
015Object Morph
Butterfly To Bee
Change the butterfly to a bee.
Prompt Guide1 input
016Object Morph
Bee To Fireflies
Change the bee into a small swarm of fireflies.
Prompt Guide1 input
017Audio Sync
Prompt Guide Building Lights
The lights of the apartments start turning on in sync with the music.
Prompt Guide1 input
018Text Animation
Word By Word Text Sync
word by word, one word on a the screen at a time: did, you, know, that, this, model, can, do, pretty,...
Prompt GuideNo exposed inputs
019Motion Graphics
Skateboard Motion Effects
Edit this keeping everything the same. Add animated motion effects coming out of the skateboard.
Prompt GuideNo exposed inputs
020Camera Motion
Camera Tilt Boots
Change the camera angle, a close-up on his shoes, quickly tilting up to medium shot, then widening.
Prompt GuideNo exposed inputs
021Multi Input
Birds Shape With Audio
The birds from <video> loosely form the imperfect shape of a bird based on <image>. They move to the...
Prompt Guide Config4 inputs
022Storyboard
Storyboard Show Me
Show me in this story. Follow the story exactly in order starting top left. Entire story in 10 seconds....
Prompt Guide Config2 inputs
023Semantic Swap
Spaceships White Origami
Change the ships to be made from white origami paper.
Prompt Guide1 input
024Semantic Swap
Astronaut Sea Anemone
Change the astronaut to a sea anemone.
Prompt Guide1 input
025Semantic Swap
Small Ships To Stingrays
Change the small ships to stingrays.
Prompt Guide1 input
Input / Output Compare
These examples prioritize samples where public input assets are exposed, making the Omni workflow easier to inspect.
010 / Violinist Transport Environment
Transport the violinist to the image environment
Input
Input video / Uses the output of 009_violinist_input as this step's input.
Output
011 / Violinist Invisible Violin
Make the violin invisible
Input
Input video / Uses the output of 010_violinist_transport_environment as this step's input.
Output
012 / Violinist Over Shoulder
Change the camera angle to be over the violinist’s shoulder.
Input
Input video / Uses the output of 011_violinist_invisible_violin as this step's input.
Output
015 / Butterfly To Bee
Change the butterfly to a bee.
Input
Input video
Output
016 / Bee To Fireflies
Change the bee into a small swarm of fireflies.
Input
Input video / Uses the output of 015_butterfly_to_bee as this step's input.
Output
017 / Prompt Guide Building Lights
The lights of the apartments start turning on in sync with the music.
Input
Input video
Output
021 / Birds Shape With Audio
The birds from <video> loosely form the imperfect shape of a bird based on <image>. They move to the music from <audio> and dissipate as they fly
Input
Input video
Input image
Output
022 / Storyboard Show Me
Show me in this story. Follow the story exactly in order starting top left. Entire story in 10 seconds. Cinematic
Input
Input image
Input image
Output