PulseAugur
实时 06:42:32

Google DeepMind unveils Gemini Omni for generative video

Google DeepMind has announced Gemini Omni, a new model designed to generate content across various modalities, beginning with video. This model integrates Gemini's AI capabilities with advanced generative media systems. Gemini Omni aims to advance understanding of the world and enhance multimodal capabilities, including editing. AI

影响 Sets a new direction for multimodal generative AI, starting with video creation.

排序理由 Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 X — Google DeepMind 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

报道来源 [1]

  1. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video.

    We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video. It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵 https:/…