Gemini Omni 1.2 Flash
videoGoogle's Gemini Omni 1.2 Flash video model. A 3 to 15 second clip with sound, at up to 4K, from a prompt, frames, or two to six reference pictures.
Other versions
What it supports
- Aspect ratios
- 16:9, 9:16
- Resolutions
- 360p, 720p, 1080p, 4k
- Duration
- 3–15s
What it costs
- 360p
- normally 4, now 3 credits per second
- 720p
- normally 9, now 7 credits per second
- 1080p
- normally 10, now 8 credits per second
- 4k
- normally 22, now 18 credits per second
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Gemini Omni 1.2 Flash is Google's Omni video model. It makes a clip with sound from a prompt, from frames, or from reference pictures. It is not Nano Banana Pro, which makes stills.
What it is good at
A clip of 3 to 15 seconds with sound, at 360p, 720p, 1080p, or 4K. Sound is part of the clip. There is no switch to turn it off.
How to use it on Visxy
Write the shot. Pick a length from 3 to 15 seconds, a resolution, and a frame: 16:9 or 9:16.
Or attach one opening picture. On a clip of 10 seconds or less you can also attach a closing picture. From 11 seconds on, only the opening picture is accepted.
For reference pictures, open Gemini Omni 1.2 Flash Reference and attach two to six. Those pictures are references, not the opening and closing frames. Auto is a frame choice on that path. The prompt does not name them with a tag.
To change a clip you already have, open Gemini Omni 1.2 Flash Video Edit.
Where it differs
Veo 3.1 is Google's other video model here. Omni 1.2 Flash adds 360p and 4K, a reference-picture path, and a separate edit for a clip you already have.
FAQ
Does the clip include sound?
Yes. There is no sound switch.
When can I set a last frame?
On a clip of 10 seconds or less. A longer clip takes the opening picture only.
How many reference pictures?
Two to six, on the reference path. One or two pictures are the frame path.
What resolutions are there?
360p, 720p, 1080p, and 4K.
Official sources
More video models
All video modelsWan 3.0 Prime
Alibaba's faster Wan 3.0. The same prompt, frames, sound switch, and reference pictures, aimed at a quicker clip.
Flux 3
Black Forest Labs' first Flux video model. A clip with sound from a prompt or from one opening picture. Flux 2 still makes the photographs.
MiniMax H3 Max Turbo
MiniMax H3 Max Turbo is the faster H3 Max tier. A clip of 1 to 15 seconds with sound, at 480p, 768p, or 1080p, from a prompt or from a start and an optional end frame.
MiniMax H3 Max
MiniMax H3 Max makes a clip of 1 to 15 seconds with sound, at 480p, 768p, or 1080p, from a prompt or from a start frame and an optional end frame.
Grok Imagine 1.5
xAI's Grok Imagine 1.5 video model. A clip from a prompt or one opening picture, or from several reference pictures without @ tags.
Grok Imagine 1.5 Lite
xAI's lighter Grok Imagine 1.5 video model. A clip of 1 to 15 seconds at 480p, 720p, or 1080p, from a prompt or one opening picture.