商业产业 The Verge AI 2026-07-07T16:31 正文 ok 279 words

Meta 新 Muse Image 模型能将其他 Instagram 用户“拉入” AI 照片

英文标题:Meta’s new Muse Image model can pull other Instagram users into AI photos

Meta 发布首个由超级智能实验室打造的 Muse Image 图像生成模型,现已在 Meta AI、Instagram 和 WhatsApp 中上线,并将登陆 Facebook 与 Messenger。该模型具备“agentic”特性,可联合 Muse Spark 语言模型进行推理、搜索与规划,还可通过 @ 提及他人账户以借用其形象生成图片。用户能涂鸦修改图像、重新设计房间等,Meta 也预告了 Muse Video 模型与 30 种 Instagram 新 AI 特效。此举为创作者和开发者提供了更丰富的生成式 AI 体验,并标志着 Muse 系列正逐步取代 Llama 模型矩阵。
打开原文相关 3 · 机会 1
media0 B media30.1 KB media90.8 KB media2.9 KB media1.5 MB media2.3 MB media526.1 KB media4.3 MB media75.1 KB media228.3 KB media42.3 KB media166.6 KB media224.4 KB media62.0 KB media60.3 KB media190.9 KB media47.7 KB media130.0 KB media251.8 KB media45.9 KB

中文

Meta 正在推出其超级智能实验室(Superintelligence Labs)部门打造的首个 AI 图像生成模型。据周二的公告介绍,Muse Image 模型现已驱动 Meta AI 应用、Instagram 和 WhatsApp 中的图像创作工具,并很快将登陆 Facebook 和 Messenger。

这是日益壮大的 Muse AI 模型家族的一部分,将取代 Meta 原有的 Llama 阵容。去年被 Meta 聘请掌管超级智能实验室的 Alexandr Wang 在 Threads 上表示,Muse Image 是“agentic”(智能体式)的,这意味着它会借助 Muse Spark 大语言模型“在生成之前对提示进行推理、搜索网络并做出规划”。Meta 还计划推出 Muse Video 模型,Wang 曾透露该视频模型“在提示遵循度、视觉保真度和时间一致性方面具有竞争力”。

Meta 还指出,用户可以在 Muse Image 的提示词中 @ 提及其他 Instagram 账户,从而让 AI 模型将相应人物的相似面貌融入生成结果。Meta 表示“标记用户名能让 Meta AI 利用公开照片构建形象”,但同时说明用户可以控制他人如何将自己的内容用于 AI。

用户还可以利用建议提示词来转换图像,并设计邀请函、明信片等。此外,Muse Image 还能依据从 Facebook Marketplace(或网络其他地方)获取的图像重新装潢房间,并允许用户直接在照片上涂鸦以进行即时修改,之后可分享到信息流、快拍或聊天。Muse Image 模型将为即将在美国推出的 Instagram Stories 中的 30 种新 AI 特效提供支持,随后将很快推广至其他国家及 Meta 应用的更多场景。

English / 原文

Meta is launching the first AI image generation model made by its Superintelligence Labs division. The Muse Image model now powers the image-making tools across the Meta AI app, Instagram, and WhatsApp, and it’s coming soon to Facebook and Messenger, according to an announcement on Tuesday.

It’s part of the growing Muse family of AI models that replace Meta’s Llama lineup. Alexandr Wang, who Meta hired to head up its Superintelligence Labs last year, says on Threads that Muse Image is “agentic,” meaning it works with its Muse Spark large language model “to reason through your prompt, search the web, and plan before it generates.” Meta is also planning to launch a Muse Video model, which Wang teased, saying it’s “competitive on prompt adherence, visual fidelity, temporal consistency.”

As noted by Meta, users can @ mention other Instagram accounts in Muse Image prompts, allowing the AI model to incorporate their likeness into its output. Meta says “tagging a username lets Meta AI use public photos to build a visual,” but notes that users can control how people reuse their content for AI.

Users can also transform images using suggested prompts and create designs for things like invitations and postcards. Additionally, Muse Image can redesign rooms based on an image pulled from Facebook Marketplace (or elsewhere on the web), and allows users to make changes directly to photos by drawing right on top of them, which they can then share to their feed, story, or chat. The Muse Image model will power the 30 new AI effects coming to Instagram Stories in the US before rolling out to other countries and in more areas of Meta’s apps soon.