Meta's Muse Image
Muse is the model family from Meta Superintelligence Labs: Muse Spark for text and reasoning in April 2026, then Muse Image, Meta's first image model, in July, with Muse Video previewed alongside it. Muse Image is the one with an API on fal, and it has its own page with the same twelve prompts.
Meta · facts checked
Which one to pick
Side by side, measured
| Model | Price | Seconds per image | 12 prompts cost | Sizes |
|---|---|---|---|---|
| Muse Image | $0.01 per image via fal | 9 to 27 | $0.12 | Any ratio from 1:16 to 16:1, rendered at Muse's own size of about 2 |
Seconds and cost are from our own runs of the same 12 prompts through each model; open a model for every picture and the request behind it.
Every version
| Version | Released | What changed |
|---|---|---|
| Muse Image meta/muse-image | Meta's first image model: prompt reasoning and layout planning, multi-photo blending, text in images, and edits by instruction or markup. Free in Meta AI; $0.01 an image through fal. |
Frequently asked questions
Is Muse Image free?
Everyday use in Meta AI is free, with heavier use in Meta's subscription plans. Through fal's API it costs $0.01 an image.
Are Muse's weights open?
Meta has not published weights for Muse Image, unlike its Llama language models; it is available through Meta's apps and its Model API.