Image model · Meta ·
Muse Image is an image model by Meta. In Endless it costs 2 credits per image and is available on every plan.
Muse Image is Meta's image model, built to follow detailed prompts closely and render small text, charts and QR codes accurately.
2 credits per image
Muse Image is the image model Meta released in July 2026, the one behind image creation in Meta AI. It follows long, detailed prompts closely and renders fine detail accurately, including small text, charts and QR codes. Every image comes out at about 2.5 megapixels, in the shape you pick or one the model chooses.
It also edits. Attach up to 10 reference images and describe the change: Muse Image changes only what you ask, keeps the rest of the picture as it was, and can combine several references into one scene. In Endless it runs in chat and on the canvas.
Next to Nano Banana 2.1 and GPT Image 2.5, Muse Image is the lower-cost option for text-heavy layouts and targeted edits. Pick one of those when you need output up to 4K.
In your workspace, open Image and pick Muse Image in the model picker.
Write a prompt, and add reference images when you want to steer the subject, style or layout.
Generate, then refine in chat or on a canvas. Every result is saved to your workspace assets.
by Google
Design-ready images and edits that keep your subject consistent
From 9 credits per image
by OpenAI
Fast everyday renders or slower, finer detail from up to 16 refs
From 1 credit per image
by Google
Hard briefs that need fine detail, accurate text and many references
From 20 credits per image
Muse Image is on every plan, including Free. Create a workspace and get 100 credits to start, plus 50 credits every week.