Google DeepMind announces the rollout of Gemini Omni 1.1 Flash on X, emphasizing controllability, faster iteration, and production-grade polish.
Following·since 27 Aug 2026·Day 8·2 sources
Google DeepMind releases Gemini Omni 1.1 Flash video model
The gist
The release gives developers finer control over generated video content and lower-cost rapid prototyping options. Professional production workflows gain 4K upscaling and longer scene continuity within a single API-accessible model.
The full picture
Google DeepMind has released Gemini Omni 1.1 Flash, a generative video model available via the Gemini API in Google AI Studio. The model adds extended scene generation by analyzing up to 10 seconds of prior video context, up from just the final second in previous versions, enabling videos up to 40 seconds total. Developers can specify first and last keyframes to generate transitions between them, upscale output to 1080p or 4K, and generate 360p draft previews up to 60% faster at one-third the cost of standard 720p resolution. The model is also accessible through the Enterprise Agent Platform API, Google Flow, and the Gemini app for AI Plus, Pro, and Ultra subscribers.
How it developed
Google DeepMind releases Gemini Omni 1.1 Flash with extended scene generation, keyframe control, 4K upscaling, and faster 360p draft mode via the Gemini API.
Sources
The daily email
Want this in your inbox?
I send a short email each morning with the stories that moved. If you would rather just read here, that works too.
Subscribe free