Google Releases Gemini Omni—A Next-Gen AI Video Builder That Can 'Simulate the World'
·2 min read
Compiled by KHAO Editorial
— aggregated from 5 sources + 8 references discovered via search.
See llms.txt for citation guidance.
✓ KHAO Verified
Google on Tuesday introduced Gemini Omni, a new multimodal AI model that combines the company’s Gemini AI models with its media-generation tools, including Veo, Nano Banana, and Genie.
Key facts
In Decrypt ’s comparison earlier this month, Nano Banana 2 outperformed OpenAI’s GPT Image 2 in anime illustration and spatial composition tests, while OpenAI’s model performed better
The announcement came during Google the reporter/O 2026, where DeepMind CEO Demis Hassabis described Gemini Omni as “their new model that can create anything from any input
The company also introduced Flow Agent, an AI assistant integrated into Google Flow that can brainstorm scenes, organize assets, recommend plot changes, and batch-edit projects
Google on Tuesday introduced Gemini Omni, a new multimodal AI model that combines the company’s Gemini AI models with its media-generation tools, including Veo, Nano Banana, and Genie
Summary
Google introduced Gemini Omni at the reporter/O 2026 as a multimodal AI model designed to generate video and other media from nearly any input. DeepMind CEO Demis Hassabis said Gemini Omni combines Gemini with media-generation models including Veo, Nano Banana, and Genie. Gemini Omni Flash is launching first through Flow and Flow Music for Google AI subscribers. The announcement came during Google the reporter/O 2026, where DeepMind CEO Demis Hassabis described Gemini Omni as “our new model that can create anything from any input.”