---
title: "Gemini Omni Flash 1.2"
description: "Google Gemini Omni 1.2 Flash: video with native audio, any length from 3 to 15 seconds, from text, a start image (optionally to an end frame), up to 6 reference images or short reference videos, or a clip to edit. Write dialogue in the prompt for lip-synced speech; one speaker per clip works best. Auto-switches variant based on what you wire."
updated: 2026-11-05
---

# Gemini Omni Flash 1.2

**Node type:** `video:gemini_omni_flash_12_t2v`  
**Category:** `video`

## Description

Google Gemini Omni 1.2 Flash: video with native audio, any length from 3 to 15 seconds, from text, a start image (optionally to an end frame), up to 6 reference images or short reference videos, or a clip to edit. Write dialogue in the prompt for lip-synced speech; one speaker per clip works best. Auto-switches variant based on what you wire.

## Pricing

- **Cost:** ~14 credits per second
- **Per-second rate:** The figure is the rate for a 5-second clip. Shorter clips can cost a bit more per second. You're always charged for the real length.

## Variant family

- **Family:** `gemini-omni-flash-12`
- **Is primary:** yes
- **All variants:** `video:gemini_omni_flash_12_t2v`, `video:gemini_omni_flash_12_i2v`, `video:gemini_omni_flash_12_r2v`, `video:gemini_omni_flash_12_edit`

## Canvas ports

These appear as port handles on the left side of the node.

| ID                     | Label                                                                                          | Details                         |
| ---------------------- | ---------------------------------------------------------------------------------------------- | ------------------------------- |
| `prompt`               | **Prompt**                                                                                     | `TEXT` _(required)_ · multiline |
| `image_url`            | **Image (image-to-video start frame)**                                                         | `IMAGE`                         |
| `end_image_url`        | **End Frame (image-to-video, requires Image, max 10s)**                                        | `IMAGE`                         |
| `reference_image_urls` | **Reference Images (max 6)**                                                                   | `IMAGE` · list                  |
| `reference_video_urls` | **Reference Videos (reference-to-video, up to 3s each: 3 for a clip of 10s or less, 1 above)** | `VIDEO` · list                  |
| `video_url`            | **Video (edit, up to 15s)**                                                                    | `VIDEO`                         |

## Sidebar config

These render as form fields in the right-side config panel when the node is selected.

| ID             | Label                     | Details                                                             |
| -------------- | ------------------------- | ------------------------------------------------------------------- |
| `duration`     | **Duration (seconds)**    | `NUMBER` · `3…15` · default: `8`                                    |
| `aspect_ratio` | **Aspect Ratio**          | `TEXT` · options: `16:9`, `9:16` · default: `"16:9"`                |
| `resolution`   | **Resolution (up to 4K)** | `TEXT` · options: `360p`, `720p`, `1080p`, `4k` · default: `"720p"` |

## Outputs

| ID      | Label               | Type    |
| ------- | ------------------- | ------- |
| `video` | **Generated Video** | `VIDEO` |

## How to prompt Gemini Omni 1.2 Flash

- **One take or several.** It cuts between shots by default. For a single take,
  write "single continuous shot, no scene cuts".
- **Multi-shot timing.** Give each shot its own time range, for example
  "[0-4s] a wide shot of the street, [4-8s] close on her face".
- **Dialogue.** One speaker per clip. Quote the exact words, keep the lines
  short, and say who speaks and how it sounds: "the old man says quietly,
  'Not today.'" For a conversation, make one clip per speaker and cut between
  them in the editor.
- **Reference images.** Up to 6 in total, up to 3 per character. Describe what
  each image is for, in the order you wire them: "the first and second images
  are the same woman, the third is her dog".
- **Edits.** One short instruction, then "Keep everything else the same", for
  example "make it night. Keep everything else the same." Every edit sends the
  clip as a file, so expect video edits to be unavailable in the EEA, the UK
  and Switzerland, for clips Omni made as well as your own footage.
- **First and last frame.** Wire a start image and an end frame and describe
  the move between them. Runs with both frames are 10 seconds at most.
- **Resolution.** Draft at 360p and keep the take you like. 1080p and 4K make
  a NEW take from the same prompt, not an upscale of the draft, so the result
  will differ.
- **Sound.** There is no audio input. Describe the sound and music in the
  prompt ("Sound design: rain on a tin roof, no music"), and add "No dialogue"
  when nobody should speak.

---

_Auto-generated from the Wireflow node registry._

Last updated: 2026-11-05

---

Documentation index: fetch https://www.wireflow.ai/llms.txt for the full list of Wireflow docs.