Video
Gemini Omni Flash
Animate a still image into a short video with Gemini Omni Flash.
- Image to video
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Gemini Omni Flash. Review your own result before publishing.
A starting point.
Start from a clear image and describe subject movement, camera direction and ambient sound.
Before you publish.
Watch for changing faces, bent objects and sound that does not match the action.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Send image_url and prompt. Select duration from 3–10 seconds and aspect_ratio as 16:9 or 9:16.
Keep the prompt focused on movement already supported by the frame. This route has no resolution or end-frame field.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for google/gemini-omni-flash/image-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
image_url | Text | Required | — |
prompt | Text | Required | Max. characters: 20000 |
aspect_ratio | Text | Optional | 16:9, 9:16 |
duration | Whole number | Optional | ≥ 3 · ≤ 10 |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Gemini Omni Flash through the API.
Start with this model ID for the endpoint featured on this page:
google/gemini-omni-flash/image-to-video
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.