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

No image
Image

Building Agentic Document Intelligence Pipelines: Creating Scientific Figures with AutoFigure

AutoFigure is a toolkit that takes text descriptions and research paper content as input and produces publication-ready scientific figures. A new tutorial from MarkTechPost walks through the full setup process, from configuring an API-backed workflow to exporting styled diagram galleries. The piece is aimed at researchers and developers looking to automate the visual documentation side of document intelligence pipelines.

No image
Image

Changelog - 8/20/26

Midjourney has pushed a round of updates to its alpha site, responding to two weeks of feedback from thousands of testers. The changelog reflects changes shaped directly by community input, both supportive and critical. Here is a look at what was addressed in this latest iteration.

OpenAI's GPT-Image-2 can now generate images without a background
Image

OpenAI's GPT-Image-2 can now generate images without a background

OpenAI has added transparent background support to its GPT-Image-2 model, available in preview through the API. Rather than removing a background after the fact, the model bakes the alpha channel directly into the generation process. The feature is enabled with a single parameter.