Gemini Omni Flash 1.1

• 🎬 Image-to-video variant of Google's Omni Flash generative video model
• 🆕 Version 1.1 is a production-ready update focused on control
• 📏 Clips can be extended in 10-second steps, to 40 seconds
• 🧠 Uses up to 10 seconds of prior context, versus one previously
• 👁️ First-and-last-frame interpolation plus prompt or preset camera moves
• ⚡ Fast low-resolution drafts for prototyping, with 4K upscaling
• 🔒 Safety filters applied to both input prompts and generated video
• 🌐 English fully supported; other languages unevaluated by Google

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 is Google's multimodal model for video, image and text tasks, optimized for video generation and able to return video output alongside text in a single model. Google DeepMind positions it as a step toward models that create and edit anything from any input, starting with video, combining Gemini's reasoning with its generative media work. This catalog entry covers the image-to-video path of the 1.1 release: you supply a still image plus a prompt, and the model animates it.

Compared with the earlier Gemini Omni Flash, Google describes 1.1 as a production-ready update offering improved control over generative video. The headline change for image-driven work is context depth: 1.1 can analyze up to 10 seconds of prior footage, where previous models referenced only the final second, which Google says improves visual consistency and narrative adherence. It also adds scene extension in 10-second increments up to a 40-second total, keeping motion, characters and audio coherent, plus first-and-last-frame interpolation, 4K upscaling, and cheap low-resolution drafts for faster iteration.

It ships alongside Gemini Omni Flash 1.1 for text prompts, Gemini Omni Flash 1.1 R2V for reference images, and Gemini Omni Flash 1.1 Edit for conversational editing of existing clips.

Google notes the Omni Flash line is a preview family, applies content safety filters to both prompts and generated video, and has fully evaluated only English prompting.