Muse Image
An image model that thinks before it draws
Latest: Muse Image (Jul 7, 2026)
MSL's image generation and editing model, launched July 7, 2026. It behaves as an agent rather than a one-shot prompt-to-image mapper: it reasons over prompts, self-refines, composes from multiple reference photos, renders legible text, and can call web search and code execution. Available in Meta AI, meta.ai, Instagram Stories (US), and WhatsApp.
Why it matters
Muse Image reframed image generation as an agent loop — reason, draw, critique, redraw — and its self-refinement emerged from RL rather than design, with quality scaling log-linearly with test-time compute. It reached #2 on Arena for text-to-image and both editing tracks and stamps a robust invisible watermark on every output.
Facts
- Ranked #2 on the Arena leaderboard for text-to-image, single-image editing, AND multi-image editing as of July 5, 2026.
- Self-refinement behavior emerged during RL training without being explicitly designed.
- Image quality improves log-linearly with test-time compute.
- Every output carries the 'Content Seal' invisible watermark that survives cropping, compression, resizing and screenshots (checker at meta.ai/identification).
Try it yourself
Check an image for the Content Seal watermark ↗ Generate via the Meta Model API ($0.01/image) ↗ Meta AI app on the App Store ↗