Gemini Omni Flash 1.1

• 🎬 Google's text-to-video model generating clips with synchronized audio
• 🆕 Production-ready 1.1 update focused on developer control over generated video
• 📏 Extend clips in 10-second steps, up to 40 seconds total
• 🧠 Uses 10 seconds of prior context, versus one second previously
• 🔧 Adds camera-move control, first/last-frame interpolation, and 4K upscaling
• ⚡ Low-resolution draft mode for faster, cheaper prototyping of ideas
• 🌐 Grounded in Gemini world knowledge and physics understanding
• 🔒 Preview-family model with safety filters on prompts and outputs

Google

Google is an American multinational technology corporation and one of the world's most valuable brands. A subsidiary of parent company Alphabet Inc., Google operates across search, cloud computing, consumer electronics, and artificial intelligence. Its…

Gemini Omni Flash 1.1 is the text-to-video entry point for Google's Omni line, a multimodal family that pairs Gemini's reasoning with DeepMind's generative media stack to produce video (with synchronized audio) alongside text in a single model. From a written prompt it renders a clip grounded in Gemini's real-world knowledge, with physics understanding intended to make motion and interactions more coherent.

Compared with the original Gemini Omni Flash, the 1.1 release is described by Google as a production-ready update centered on control. The most concrete change: when continuing a scene, the model now conditions on up to 10 seconds of prior context, where earlier models referenced only the final second, which Google credits with better visual consistency and narrative adherence. Videos can be extended in 10-second increments to a 40-second total, with the last 10 seconds used as context to keep motion, characters and audio coherent. Also new are explicit camera-movement control, first-and-last-frame interpolation, 4K upscaling, and a fast low-resolution draft mode for cheaper iteration.

The same 1.1 generation covers other input modes: image-to-video, R2V for reference-guided generation, and Edit for conversational revision of existing footage.

Google positions Omni as conversational video creation and editing, applies content safety filters to both prompts and generated video, and notes that English is fully supported while other languages remain unevaluated.