What is Muse Image?

Muse Image is Meta’s flagship image model, available on NightCafe as a single PRO model. It costs 2 credits per image. On AI Creator and above, a single Muse Image generation is unlimited (no credits).

What it’s good at

• Prompt-faithful generation — Muse plans the image from your brief. Name the layout, props, camera, and light, not just a subject.
• Prompt to Edit — add a start image and describe the change. Muse keeps the rest of the frame and rebuilds only what you asked.
• Multi-image fusion — up to 10 start images. Give each one a job in the prompt (“the woman from the first image”, “the coat from the second”).
• Typography — quote the exact words you want on the image, and keep each string short.
• Real-world details — Muse looks up places, products, and facts while it plans. Name the real landmark or figure you want.
• Charts and infographics — write the actual numbers into the prompt so bars, tables, and labels follow your data.
• Consistent characters — keep a character looking the same across creations.

How to use it

In Studio, pick Muse Image from the model picker, write a prompt, optionally add start images, then Generate.

Write a brief the way you would brief a photographer: who or what is in frame, what they are doing, where they are, the camera angle, and the light. Open with what the image is for — “an editorial header for a meal-kit blog” — so Muse composes toward that job.

An editorial header photograph for a meal-kit brand blog. A woman in her thirties with dark curly hair tied back, wearing a striped apron over a white tee, plates a bowl of roasted vegetables and grains at a light oak kitchen counter. Even midday daylight from a window behind the counter. Waist-up shot from slightly above, 35mm lens, shallow depth of field with the bowl and her hands sharp. Photoreal editorial food photography, bright natural palette.

To edit an existing photo, add it as a Start Image (or use Prompt to Edit) and describe only the change. Name what stays.

Remove the cardboard moving box on the rug and the black laundry basket beside the armchair, and continue the oak floor and the rug pattern where they stood. Keep the sofa, the coffee table, the armchair, the curtains, the daylight, and the camera position exactly as they are.

For text in the image, put the exact copy in quotation marks and give it a place and a job.

A modern gym storefront photographed straight on from the pavement, with a large white vinyl decal applied across the window glass. The decal reads "NEW MEMBER OFFER" in heavy condensed uppercase across the top and "$0 JOINING FEE UNTIL MARCH" in a lighter weight on the line below.

Good to know

• Muse Image is PRO and costs 2 credits per output. Start images do not change the price.
• On AI Creator and above, a single image is unlimited. Generating 4 images at once still costs credits, because that job is above the unlimited cap.
• Output is High Res (2K). Choose the aspect ratio in Settings, or match a start image.
• You can generate up to 4 images at once, and attach up to 10 start images.
• There is no Seed control — each generate is a fresh take. Save the result you like.
• Meta applies its own content filter. A prompt or result can be blocked on Meta’s side.