What is Gemini Omni 1.2 Flash Image to Video?

Gemini Omni 1.2 Flash Image to Video animates a supplied image into a video with synchronized audio. A prompt guides subject movement, camera work, dialogue, or ambient sound. The image provides the first frame, giving creators a visual starting point for short video workflows on each::labs.

How does Gemini Omni 1.2 Flash Image to Video handle an end image?

Gemini Omni 1.2 Flash Image to Video accepts an optional ending image for first-to-last frame interpolation. Supply both images and describe the transition you want between them. With an ending image, the maximum duration is 10 seconds; requests for 11 to 15 seconds are rejected before video generation.

What output can Gemini Omni Flash Image to Video create?

Gemini Omni 1.2 Flash Image to Video supports 360p, 720p, 1080p, and 4k output in landscape or portrait format. Without an ending image, the optional duration can range from 3 to 15 seconds. This lets creators animate a still image while choosing a supported format for their workflow.

Google | Gemini Omni 1.2 Flash | Image to Video.

Google
Image to Video
$0.0232–$0.2085 per second, depending on resolution

Gemini Omni 1.2 Flash Image to Video turns still images into videos with synchronized audio.

View API docs

Request

Prompt *

Create a 15-second horizontal, high-energy premium product commercial for the matcha product shown in the reference image. Preserve the exact packaging, colors, logo, typography, and proportions throughout the video.

Set in a beautiful Japanese-inspired environment with a light wooden table, vibrant green matcha powder, bamboo utensils, ceramic bowls, and soft natural sunlight.

Begin with a fast cinematic push-in toward the product as vibrant green matcha powder bursts into the air in slow motion. The camera smoothly orbits around the packaging while matcha leaves swirl elegantly, creating energetic transitions. A silky stream of matcha pours into a ceramic bowl, forming mesmerizing green swirls and delicate bubbles.

Transition seamlessly into a striking hero shot of the product standing upright, surrounded by floating matcha particles and soft golden sunlight. End with a dramatic close-up of the packaging, perfectly sharp and facing the camera.

Female voiceover (energetic, warm, natural):

"Your daily ritual, reimagined. Rich, smooth, vibrant matcha. A little moment of calm, with every sip."

Style: vibrant luxury beverage commercial, fast dynamic camera movements, seamless transitions, photorealistic liquid physics, rich emerald green tones, soft volumetric lighting, shallow depth of field, cinematic slow motion.

Image URL *

End Image URL

Aspect Ratio

Resolution

Duration

00:00

What Google | Gemini Omni 1.2 Flash | Image to Video is good at.

Related model
Gas Station Dance
Run it on the same input to compare output, speed and price.
View model

Model documentation

About this model

Gemini Omni 1.2 Flash Image to Video turns still images into videos with synchronized audio. Animate a first frame or connect first and last frames in a clip.

Questions about this model

The short answers. For anything specific to your setup, talk to our team.

Talk to an engineerPlan for your expected volume.

Gemini Omni 1.2 Flash Image to Video animates a supplied image into a video with synchronized audio. A prompt guides subject movement, camera work, dialogue, or ambient sound. The image provides the first frame, giving creators a visual starting point for short video workflows on each::labs.