Google releases Omni Flash video model with 1080p and 4K options

Google is pushing its AI video generation capabilities into territory that actually matters for professional content: high-resolution output. The company’s Omni 1.1 Flash video model now offers 1080p and 4K options, a meaningful upgrade from the 720p native resolution that shipped with the original Gemini Omni Flash earlier this year. Gemini Omni Flash, first unveiled at Google I/O on May 19, 2026, is a multimodal generative AI model from Google DeepMind. It takes combinations of text, images, audio, and video as inputs, then generates short video clips with synchronized audio. The original model outputs video clips between 3 and 10 seconds in length at 720p resolution. The addition of 1080p and 4K output changes the calculus for creators who need footage that doesn’t scream “AI-generated” the moment someone watches it on a decent monitor. One of the model’s more notable features is its conversational, multi-turn editing workflow. Rather than generating a clip and starting over if something’s off, users can refine outputs through natural language instructions. Tell it to change the lighting, swap a character’s outfit, or adjust camera angle, and the model attempts to maintain chara...