gen‑ai.news
← Back
Image

Meta's new Muse Image model accepts Instagram accounts as a prompt

Meta's new Muse Image model accepts Instagram accounts as a prompt

Meta has unveiled a new generative image model called Muse, which introduces an unusual prompting mechanism - the ability to use an Instagram account as direct input. Rather than relying solely on text descriptions, users can point the model to an Instagram profile, allowing Muse to draw on the visual content and aesthetic patterns found there to guide image generation. It is one of the more concrete examples of a social platform leveraging its own user-generated content ecosystem as a functional part of an AI product.

Beyond the Instagram prompting feature, Muse is being deployed across two other Meta surfaces. On Instagram, it is powering new generative effects within Stories, giving users AI-assisted creative options in a format that already sees heavy daily engagement. In WhatsApp, it is being used to expand the app's existing image generation capabilities, bringing the model to a messaging context where visual generation has been gradually growing in presence.

The use of Instagram accounts as prompts raises questions worth noting. When a model is conditioned on a specific account's post history, it is effectively learning and reproducing stylistic signals from that user's real uploaded content - their color choices, subject matter, composition preferences, and so on. This could offer a more personalized generation experience, but it also invites scrutiny around consent, data use, and how closely outputs might mirror the work of other creators whose public accounts could theoretically be used as prompts.

Meta has been steadily building out its generative AI presence across its family of apps, and Muse appears to be a step toward tighter integration between its social data assets and its AI tooling. Whether the Instagram-as-prompt feature becomes a widely used creative tool or a more niche capability will likely depend on how much creative control users feel it actually gives them - and on how Meta addresses the broader questions its design naturally raises.

Read at Engadget →
Share:X

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

Canva Adds Toggle to Disable Generative AI Features
Image

Canva Adds Toggle to Disable Generative AI Features

Canva is rolling out a setting that lets users turn off most of its generative AI tools, including AI image generation and features like Magic Expand. The option also reduces the amount of AI-generated content surfaced in the platform's content library. A subset of AI-powered tools - background removal and object selection - remain on by default, as Canva classifies them as editing aids rather than generative features.

Microsoft Launches MAI Image 2.7 Among Seven In-House Models at Ignite
Image

Microsoft Launches MAI Image 2.7 Among Seven In-House Models at Ignite

Microsoft revealed seven new models under its MAI brand at the Ignite 2026 conference, including an image generation model, MAI Image 2.7, alongside code, security, and language models. The strategy is explicitly about replacing third-party AI model costs with cheaper in-house alternatives across Microsoft's own products. The image model is one of several being built to run continuously in enterprise AI agent workflows.

Lightroom Alternative ACDSee Photo Studio Is Leaning Heavier Into AI
Image

Lightroom Alternative ACDSee Photo Studio Is Leaning Heavier Into AI

ACDSee Photo Studio has released version 27, adding a range of new features with a notable emphasis on AI-powered tools. The update positions the software as a more competitive option against Adobe Lightroom for photographers looking for alternatives. Several of the new capabilities target common editing workflows where AI assistance can meaningfully reduce manual effort.