Gemini Omni 1.1 Flash lets you build with more control
deepmind ·
Google DeepMind has introduced Gemini Omni 1.1 Flash, a production-ready update for developers that adds new creative controls for generative video. The model allows scene extension in 10-second increments up to 40 seconds total, using up to 10 seconds of prior context for better visual consistency. Developers can specify first and last frames to create smooth transitions and camera movements, and can generate 360p previews that are up to 60% faster and a third of the cost of 720p output. Final projects can be upscaled to 1080p or 4K resolution, and video references of up to three seconds can be included in multimodal inputs. The model is available through Google AI Studio and the Gemini Enterprise Agent Platform, and is also rolling out to Google Flow and the Gemini app for subscribers. Customers including Adobe, Figma Weave, GMI Cloud, and Runway are already integrating the model into their products.
deepmind