Gemini Omni 1.1 Flash
A Gemini model for video generation and multimodal creation
About Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash is a multimodal model for video, image, and text tasks, optimized for video generation. It can output video and return a text response within the same model. It supports analyzing up to 10 seconds of prior video context, extending videos in 10-second increments, and controlling transitions by specifying a shot's first and last frames, making it suitable for generative video workflows, creative tools, and media editing software development.
Best for
Best use cases
Extend video stories
Control shot transitions
Create video drafts quickly
Develop generative video applications
Compare before choosing
The official comparison page says that earlier models could reference only the final second of a video, while Omni 1.1 can analyze up to 10 seconds of prior context.
Features
Extend video stories
Analyze up to 10 seconds of prior context and extend videos in 10-second increments, up to 40 seconds total.
Control first and last frames
Specify a shot's starting and ending frames to generate continuous video between two keyframes.
Efficient draft production
Generate lightweight 360p previews, up to 60% faster than standard 720p, for rapid prototyping and storyboard iteration.
Multimodal video generation
Supports video, image, and text tasks, optimized for video generation.
Pros
- Can analyze up to 10 seconds of prior context to improve visual consistency and narrative alignment.
- Videos can be extended in 10-second increments, up to 40 seconds total.
- Supports specifying the first and last frame of a shot, helping create continuous transitions, orbiting, and zoom shots.
- 360p previews can be accelerated by up to 60%, at one-third the cost of standard 720p.