Google released Gemini Omni 1.1 Flash, an update to its video-generating model aimed at developers building creative and editing tools. It can continue an existing clip using the previous ten seconds as context, generate video between a chosen first and last frame, produce cheap low-resolution drafts, and upscale finished work to 4K. It is available through the Gemini API and the Enterprise Agent Platform, with scene extension also reaching paid Gemini app subscribers.
What changed
Earlier models referenced only the final second of a clip when continuing a scene, and lacked 4K output.
What it unlocks
Continuing an existing AI-generated video in 10-second steps with consistent characters, and setting the opening and closing frames of a shot.
- 10 seconds of prior context
- extensions up to 40 seconds total
- 360p up to 60% faster
- 360p at a third of 720p cost
What you need to act on it
- Gemini API access via Google AI Studio or the Gemini Enterprise Agent Platform
- a Google AI Plus, Pro or Ultra subscription for Flow and the Gemini app
Sources