
Google has released Gemini Omni 1.1 Flash, a video generation and editing AI. It can now extend scenes using up to 10 seconds of context.
Videos can be extended to a maximum of 40 seconds.
The model is production-ready and available to developers.
What happened
Google announced Gemini Omni 1.1 Flash on August 27, a multimodal AI model for video generation and editing, available to developers via the Gemini API and Google AI Studio.
Why it matters
The update makes Omni 1.1 production-ready for professional use. The key enhancement is scene extension, which now analyzes up to 10 seconds of prior context (vs. the previous 1 second), improving visual and narrative coherence. Videos can be extended in 10-second increments up to 40 seconds total.
What to watch
A 360p draft mode generates up to 60% faster and at one-third the cost of the standard 720p, with final output upscalable to 1080p or 4K. Adobe has already integrated Gemini Omni Flash into Adobe Firefly.
Ask the AI about this article →
This launch marks a significant step for Google in the competitive AI video generation space. By making the model production-ready, Google is signaling that it is ready for commercial use, not just experimentation. The improved scene extension, with 10 seconds of context, allows for more coherent and visually consistent video continuations, which is critical for professional storytelling. The addition of a low-cost 360p draft mode is a strategic move to encourage rapid iteration in pre-production, making the tool more accessible for storyboarding and prototyping.
The integration with Adobe Firefly and availability through the Gemini Enterprise Agent Platform highlight Google's push to embed the model into existing creative and enterprise workflows. The inclusion of SynthID watermarking ensures traceability of AI-generated content, a growing concern in the industry. While the article does not state the exact pricing, the cost efficiency of the draft mode is likely to appeal to studios and independent creators alike, potentially accelerating the adoption of AI-driven video production in commercial settings.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Anthropic PBC previewed the Model Hardware Standard (MHS), a unified interface that lets AI agents control sci…
Honor has moved its Robot Phone from an internal debate to a mass-produced commercial product, more than a yea…

A survey by Japanese research firm Parol General Research Institute found that among regular employees, AI usa…

ZEALS and Timee announced a partnership on August 27, 2026, to create a new work category called "data collect…

Nvidia has taken a minority stake in Cloverleaf Infrastructure, a developer that secures powered land and util…

Russian-speaking hackers used SpaceX's Cursor AI agent to breach a Belgian chemical company and six other firm…
