Meta Platforms released Muse Image on July 7, a text-to-image generation model available to users at no cost through the Meta AI app, WhatsApp direct messages, and Instagram Stories. The tool, previously codenamed Mango, allows users to generate, edit, and remix images from text prompts, sketches, and existing photos, and will power more than 30 new AI effects for Instagram Stories.
Developed by Meta Superintelligence Labs under Alexandr Wang, Muse Image is the division's second major release following the Muse Spark language model in April. Internal benchmarks show the model trailing OpenAI's GPT Image 2 but outperforming Google's Nano Banana 2. Users who exceed free limits can switch to Meta One, a subscription plan introduced in May.
The model also powers advertiser-specific tools within Meta's Advantage Plus service and integrates with Facebook Marketplace for interior visualisation. Meta plans to expand Muse Image to Facebook, Messenger, and additional countries later in 2026, with a video generation model expected to follow.