Gemini Omni Flash 1.1 AI video generator

VideoGemini Omni Flash 1.1ResolutionAspect ratioDuration
Create now

Google's updated video model. Type the shot, then direct it.

Every video model

One workspace
Gemini Omni Flash 1.1Google DeepMind
Veo 3.1Google DeepMind
Seedance 2.5ByteDance
Kling 3.0 TurboKling
MiniMax H3 Maxfal.ai
Happy Horse 1.1Alibaba
Flux 3Black Forest Labs

Made with Gemini Omni Flash 1.1

Generate now

Key features

Conversational editing

Say the change and it lands on the same take: a new sky, a rewritten sign. Everything you did not mention stays as shot.

Video extension

Grow a clip ten seconds at a time, up to a 40-second scene. The join comes from your final frames, so motion carries through.

Reference to video

Up to ten images and three short clips steer one generation, each tagged as a subject, style, or setting in the prompt.

Character consistency

Faces, wardrobe, and voices hold across cuts and across successive edits, without re-uploading the reference each turn.

Native audio and dialogue

Sound is generated with the picture: spoken lines, effects, ambience, and music timed to the action. Write audio in the prompt.

Up to 4K output

Draft at 360p, master at 720p, then deliver the same take at 1080p or 4K through the built-in upscale, all from one prompt.

What Gemini Omni Flash 1.1 generates

Sound-on scenes from a sentence

Write the shot and the audio together and both come back at once: the action, the room tone, the line the character speaks, lip-synced. The sound you name is the sound you get.

A busy ramen kitchen at night with steam rising through hanging lamps as a cook plates noodles

Edits you type

Generate, then direct: relight the scene, swap the wardrobe, rewrite the sign. Each instruction lands on the same take while everything you did not mention stays exactly as shot.

Split frame of the same man on a rainy stone bridge, charcoal coat on the left and yellow raincoat on the right

Scenes that grow to 40 seconds

Start with a ten-second beat and extend it in ten-second steps. The model reads your final frames and continues the motion, cast, and score, so the joins read as one take.

Four-panel filmstrip of a red train crossing a stone viaduct at dusk toward a lit village

Reference-true characters and products

Up to ten images and three short clips pin who and what is in the shot. A character keeps their face, clothing, and voice from the first generation to the last edit.

Reference cards of a watch and a model pinned beside the finished campaign frame on dark linen

Generate a video in three steps

  1. 01

    Open Morphic

    Sign up and start generating on a free-flowing, infinite visual canvas.

  2. 02

    Write the shot with its sound

    Subject, action, camera, light, and the audio. Say what happens when, and whether it plays as one continuous shot or cuts.

  3. 03

    Generate, then direct

    Refine the take in follow-ups: one change per turn, and extend it when the scene needs room.

Generate now

Related workflows

Cinematic scene

One image to a 9-scene cinematic video.

Try this workflow

Time-freeze effect

Cinematic time-freeze short film for any scene

Try this workflow

Short film creator

Go from any idea to a finished short film with scenes, visuals, video, and music.

Try this workflow

Video style transfer

Restyle any video in a completely new visual style. Every frame transforms, all motion stays intact.

Try this workflow

Color grade cinema

Set the look with one reference image. Apply that exact grade to any scene or batch.

Try this workflow

Renovation timelapse

Photo of any real-estate becomes a cinematic renovation timelapse video with construction SFX and music.

Try this workflow

All on Morphic

Your complete video stack

Models

Gemini Omni, Veo 3.1, Seedance 2.5, Kling 3.0, and more. Pick the one that fits the shot and swap mid-project.

Frames to video

Set 2 to 5 keyframes, describe the motion, and Morphic fills the in-between. Time Control tunes how long each frame holds.

Lip sync

Match a performance to a recorded line, or give a character a different voice, without regenerating the shot around them.

Workflows

Turn a finished sequence into a one-click Workflow. Rerun it, share the link, or favorite it for fast reuse.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

1100 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

Can I use a Gemini Omni Flash 1.1 AI video generator right now?
Yes. Type the shot into the prompt bar above and generate, with everything running in the browser and nothing to install. Morphic runs Gemini Omni alongside Veo 3.1, Seedance 2.5, Kling, and the rest of the video catalog, so the same brief can go through several models and come back side by side on the Canvas.
What is Gemini Omni Flash 1.1?
The second release of Google DeepMind's multimodal video model, shipped in late August 2026. It generates 3 to 10 second clips with native audio from text, images, and video references, then keeps working on them: follow-up prompts edit the same take, and extensions grow it to 40 seconds. Version 1.1 added the resolution ladder up to 4K, working video references, and first-to-last-frame interpolation.
What makes this video generator different from a standard text-to-video tool?
The generation is a conversation, not a one-shot render. After the first take you say what to change, in plain language, and the model applies it while the rest of the frame stays as shot: faces, wardrobe, and voices carry across every turn. A standard generator makes you re-roll the whole clip and hope; this one lets you keep the take and fix the detail.
Does the Gemini Omni Flash 1.1 video generator include sound?
Yes, sound is generated in the same pass as the picture: dialogue with lip sync, effects, ambience, and music timed to the action. Write the audio into the brief the way you write the visuals, because a prompt that says nothing about sound gets a soundtrack the model chooses on its own. Even silence is something you ask for.
How long can a generated video be?
A single generation runs 3 to 10 seconds. From there, extension continues the clip ten seconds at a time up to 40 seconds total, reading the last stretch of footage so motion, characters, and audio stay continuous across the join. That turns a short take into a full scene without stitching clips by hand.
What resolution does Gemini Omni Flash 1.1 generate?
Four options, in 16:9 or 9:16: 360p for cheap drafts, 720p native, and 1080p or 4K produced as upscales of the take. The practical workflow is to iterate at a low resolution until the shot is right, then request the delivery resolution once, rather than paying for 4K on every attempt.
Can it work from my images and clips?
Yes. Animate a single still, hand it a first and last frame to interpolate between, or attach up to ten reference images and three short clips that pin a character, product, setting, or style. The same image used as both first and last frame comes back as a seamless loop.
How do I generate a video online without installing anything?
Everything runs in the browser on Morphic, with no download or install. Type the prompt, generate, and the render lands on your Canvas, from any laptop, including machines with no GPU. From there you can refine the take in follow-ups, run the same brief through another model, and compare the results side by side.

You might also like