Gemini Omni 1.1 Flash lets you build with more control
Omni now delivers studio-quality video production, including the ability to extend a scene, first and last frame interpolation, crisp 4K upscaling, faster prototyping, and more. We are introducing Gemini Omni 1.1 Flash, a production-ready update for developers that offers improved control over generative video. You can now extend scenes, specify start and end frames for…
Opening of the original on Google DeepMind Blog
Summary
Google DeepMind released Gemini Omni 1.1 Flash, a production-ready update for developers offering enhanced control over generative video. The model now analyzes up to 10 seconds of context for scene extension, allows specifying start and end frames for smooth transitions, and generates 4K output. Developers can also create faster, lower-cost 360p previews for rapid prototyping. This update aims to make generative video more controllable, faster to iterate on, and polished for real-world deployment.
Why it matters
This update makes Google's Gemini Omni 1.1 production-ready for professional video generation, a significant step beyond research previews. By allowing developers to extend scenes with longer context and precisely control transitions via keyframes, it offers more granular creative control. This directly competes with other labs developing advanced video generation tools. The faster, cheaper 360p previews are a clear benefit for iterative workflows, potentially speeding up development cycles for creative software. Future developments will likely focus on further increasing generation length and fidelity.
Related: OpenAI: First impressions of GPT-6 Astra from developers · Anthropic: Claude Science, an AI workbench for scientists · Microsoft: What's new in AI? · Meta: Nvidia launches free tool that links idle computers into a personal AI data center · xAI: Use 14 references in Grok Imagine videos
Rated middle: a real update, not a headline event.
- AI News: OpenAI Made a Massive Move Against NVIDIAMatt Wolfe · Web · Aug 28, 2026
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool PrimitivesarXiv cs.AI · Web · Sep 1, 2026
- Four major AI models suffer rare overlapping downtimeArs Technica AI · Web · Sep 3, 2026
- Google’s latest AI weather model gives you no excuse to forget your umbrellaTechCrunch AI · Web · Sep 3, 2026
- Google releases Gemini 3.8 Flash, its third Flash model in six weeksArs Technica AI · Web · Sep 2, 2026
- Claude Fable 5.1 made me a really nice animated pelicanSimon Willison · Web · Sep 1, 2026
- Gemini Omni 1.1 Flash lets you build with more controlThe Keyword: Gemini
- Gemini Omni 1.1 Flash lets you build with more controlThe Keyword: Developers
- Gemini API Cookbook: feat(quickstarts): update Gemini Omni Flash quickstart to Omni 1.1 (#1350)Gemini API Cookbook
- From Atari to EVE Online: Building on 15 Years of AI Research in GamesGoogle DeepMind Blog
- Google DeepMind and A24 announce first-of-its-kind research partnershipGoogle DeepMind Blog
- Investing in multi-agent AI safety researchGoogle DeepMind Blog
Questions people ask
- What is Gemini Omni 1.1 Flash?
- It is a production-ready update to Google's Gemini Omni generative video model, offering developers more control over video creation and editing.
- How does scene extension work in Omni 1.1 Flash?
- The model can now analyze up to 10 seconds of prior video context to seamlessly continue generating footage, allowing for longer narratives up to 40 seconds.
- What are the benefits of the 360p previews?
- These lightweight previews generate up to 60% faster and at a third of the cost, aiding rapid prototyping and storyboard iteration for developers.
More from Google DeepMind Blog 99 more
Page generated Sep 3, 2026. Summaries are Subvolts' own; the story belongs to Google DeepMind Blog.