> For the complete documentation index, see [llms.txt](https://docs.pletor.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.pletor.ai/models/video-models/gemini-omni-flash-1.md).

# Gemini Omni Flash

Google's lasted model for video generation and editing.

### Gemini Omni Flash 1.2

The current version: 15-second generations and edits, extension, 4K output, and a dedicated upscaler. Draft at 360p or 720p, then upscale the keepers to 1080p or 4K.

* **15-second clips**: generate and edit up to 15 seconds, set from 3 to 15.
* **Four modes**: First frame (optional end frame, or text-to-video), Reference, Edit, Extend.
* **References**: up to 10 images and 3 videos of up to 15 seconds each, cited as `<IMAGE_REF_0>`, `<VIDEO_REF_0>` (numbering starts at 0).
* **Extension**: continue a clip by 3 to 10 seconds.
* **360p to 4K**.
* **Weaknesses**: 16:9 or 9:16 only (Auto follows the first frame's orientation); extension and first-to-last-frame interpolation stop at 10 seconds.

**Gemini Omni Flash 1.2 Upscale**, in the Upscale video node: takes clips up to 15 seconds to 720p, 1080p or 4K. The target must be above the source resolution, and a 360p clip goes to 720p first before 4K.

***

### Gemini Omni Flash (original)

Generates from text, image, and video inputs, and lets you refine results through natural language.

Best suited for short clips and iterative editing.

Caps at 10 seconds. Prefer [Seedance 2.0](https://docs.pletor.ai/models/video-models/seedance-2.0.md) or [Kling 3.0](https://docs.pletor.ai/models/video-models/kling-3.0.md) for longer durations or production-grade cinematography.

#### Key updates

* **Multimodal referencing:** Combine text, image, and video inputs in one generation to control composition and maintain consistency.
* **Conversational video editing:** Refine and edit videos using natural language, no need to re-generate from a full prompt for small changes.
* **Real-world knowledge:** Draws on Gemini's general knowledge (history, biology, narrative logic) to construct more coherent scenes.

#### Weaknesses

* **10-second cap:** Generations are limited to 10 seconds; longer durations are planned but not yet available.
* **Limited aspect ratios**: 16:9 or 9:16.
* **Video reference limitation:** Short video references (up to 3s) are accepted by the request schema but aren't correctly processed by the model yet.
* **Consistency across scene changes:** Character consistency can degrade during scene changes or panning movements.
