Google DeepMind·2026-05-18 03:50· 2026-05-18

Introducing Gemini Omni

AI summary

Google DeepMind released Gemini Omni Flash, the first model in the Gemini Omni family, generating high-quality video from combined image, audio, video and text inputs and supporting iterative video editing through natural-language conversations.

Selection record

Threshold 60Official, first-handFirst 82Second 87

AdmittedSum of both 169 ≥ twice the threshold 120

Source tier: Official, first-hand; this tier's threshold is 60
Pre-filter: passed：Gemini Omni多模态生成模型发布
Why it was chosen: Combining conversational video editing and multimodal inputs in one model indicates changes to video-creation workflows.

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.

Source: Google DeepMind · deepmind.google

#Model releases #Multimodal #Video #Google