Motion study
“Rain falls on a busy city crosswalk at night, umbrellas crossing, neon reflections rippling on wet asphalt, slow high-angle drift.”
video model
Create AI video with Gemini Omni Flash
Gemini Omni Flash is Google’s multimodal Gemini Omni video model, generating 3 to 10 second clips at 24 FPS from a text prompt or a start image in landscape or portrait.
$0.10 / second at provider cost for members — see the full price breakdown
What you need to start
Describe the scene and motion, or add a start image to animate.
Loading...
Original results
Gemini Omni Flash examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Image-to-video
“Animate with light slowly shifting through the misted glass, ferns swaying gently, and drifting particles.”
Creative scene
“Paper lanterns sway above a narrow old-town alley at blue hour as the camera glides forward beneath them.”
Scene brief
“Set the scene as a still before describing its motion.”
Start-frame control
“Use this image as the opening composition.”
Composition brief
“Establish framing and light, then hand the motion to the model.”
Where Gemini Omni Flash fits best
Best uses
- Natural scene motion from concise prompts
- Animating a still image with believable physics
- Landscape and portrait social clips
- Consistent results across follow-up generations
Limits to know
- Made currently exposes two aspect ratios (16:9 and 9:16) and provider-managed resolution.
- Clips are capped at 10 seconds; longer sequences need to be generated in parts and edited together.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- 16:9, 9:16
- Resolution
- Provider-managed (720p-class output)
- Duration
- 3–10 seconds
- Output formats
- MP4
- Reference images
- 1
- Processing
- Varies with queue and duration; progress appears in the generation view.
How to use Gemini Omni Flash in Made
- 1
Describe the scene
Name the subject, environment, and the one or two motions that matter most.
- 2
Add a start image if you have one
Upload a still to animate when the composition is already decided.
- 3
Pick orientation and length
Choose 16:9 or 9:16 and a duration from 3 to 10 seconds.
- 4
Generate and review
Check motion believability and edges, then refine the motion language if needed.
Compare relevant models
video
MiniMax H3 Max
MiniMax H3 Max is a speed-focused, post-trained variant of the H3 video model, generating 5 to 15 second clips at 480P or 768P with strong prompt adherence — often in a few seconds.
Explore model →video
Grok Imagine Video 1.5
Grok Imagine Video 1.5 is xAI’s current video model in Made, generating 1 to 15 second clips with audio on by default at 480p to 1080p, from a text prompt or a start image.
Explore model →agent
Made Auto
Upload an image or describe the result you need. Made Auto interprets the request, selects an available Made tool, and keeps follow-up edits in one conversation.
Explore model →Continue with a related tool
AI Video Generator
Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.
Open tool →AI Image Generator
Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
Open tool →It is the Flash tier of Google’s Gemini Omni multimodal video family, focused on fast, natural short-clip generation from text or an image.