Google DeepMind 宣布发布两款新模型：Nano Banana 2 Lite 和 Gemini Omni Flash。Nano Banana 2 Lite 专为快速文本到图像生成而设计，仅需四秒即可生成输出，非常适合快速构思和成本敏感的工作流程。Gemini Omni Flash 是一款多模态模型，专注于对话式视频编辑、现实世界知识集成以及将文本/图形与视频动作连接起来，现已通过 Gemini API 和 Google AI Studio 访问。 AI
影响 新模型提供更快的图像生成和先进的视频编辑功能，可能加速创意工作流程和多模态人工智能应用。
排序理由 前沿实验室模型发布，附带系统卡。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
Find out more → https://t.co/feTpTwfnmC https://t.co/C527I57Xy3
Pair these models together using the Interactions API. 🤝 Quickly generate an image with Nano Banana 2 Lite, then immediately animate it using Gemini Omni Flash. Plus, you can maintain session history to stack up to three sequential edits. https://t.co/y9PVQPhYz1
Gemini Omni Flash shines in: 🔵 Conversational video editing 🔵 Multimodal referencing and combining inputs 🔵 Real-world knowledge 🔵 Connecting text and graphics directly to video actions It’s available in @GoogleAIStudio, the Gemini API and Gemini Enterprise Agent Platform https…
We’re shipping 2 major releases: 🔘 Nano Banana 2 Lite: our fastest and cheapest Gemini Image model 🔘 Gemini Omni Flash: now available via the Gemini API and in @GoogleAIStudio to help developers generate and edit high-quality videos. https://t.co/fqB2sA5Xyl
Nano Banana 2 Lite delivers text-to-image outputs in just 4 seconds. It’s designed for quicker ideation and workflows where speed and cost are the primary roadblocks. https://t.co/KJ51Ps70eC