Meta 发布 Muse Image 并预览 Muse Video，具备智能体式图像生成能力

AI 摘要

Meta 超级智能实验室发布了 Muse Image 并预览了 Muse Video，这是其首批媒体生成模型。Muse Image 具备智能体能力，能使用搜索和编码工具、自我优化，并支持多参考图像合成，已在 Meta AI 应用、meta.ai 等平台上线。Muse Video 提供高保真视频生成和原生音频支持，即将面向创作者推出。模型在 Arena 基准上排名靠前，并内置 Content Seal 水印系统以验证 AI 生成内容。

正文节选

We’re excited to launch Muse Image and preview Muse Video, the first media generation models developed by Meta Superintelligence Labs. Muse Image is our most advanced image generation model yet: it follows instructions faithfully, edits with precision, and composes from multiple references. It also brings agentic tool use capabilities and integrates with Muse Spark. Muse Video, built on the same pretraining base, delivers exceptional visual fidelity with native audio support. Muse Image is avail

发布时间：—

抓取时间：2026-08-02 00:09

来源机构：Meta