Overview
- Muse Image, released Tuesday, is Meta Superintelligence Labs’ first in-house image‑generation model and is live in the Meta AI app, Instagram Stories and in WhatsApp in select countries.
- The model accepts complex text prompts and photo inputs, supports multi‑reference composition, sketch and annotation edits, and uses Muse Spark reasoning to plan and refine outputs.
- Everyday image creation is free but higher volumes and advanced features are gated behind Meta One subscriptions and advertisers will get access through Advantage+ creative in the coming weeks.
- Meta published internal benchmarks showing Muse Image trails OpenAI’s GPT Image 2 on some measures while outperforming Google’s Nano Banana 2 on certain editing tasks, and the company previewed a Muse Video model.
- A default tagging feature lets users pull public Instagram photos into generated images unless they opt out, which has drawn immediate privacy concerns and renewed scrutiny over how Meta uses public content.