A cheap multi-reference model
Most models that combine many references cost 14–27 credits. Muse Image does it for 3.3, which makes it a good way to try combines before re-running the best one on Seedream or GPT Image 2.
Muse Image is Meta's image model, the first from Meta Superintelligence Labs. On Kenerate it costs 3.3 credits and composes with up to 10 reference images.
Quick answer
Updated
Muse Image is Meta's image model, announced on 7 July 2026 as the first image model from Meta Superintelligence Labs. Meta says it follows instructions faithfully, edits precisely and composes from multiple references, and marks images with an invisible Content Seal. On Kenerate, Meta Muse Image costs 3.3 credits and takes up to 10 reference images — one of the cheapest multi-reference models here.
About the model
Facts from the maker's own announcement and repository, linked below.
| Maker | Meta Superintelligence Labs |
|---|---|
| Announced | 7 July 2026 |
| Meta's highlights | Faithful instruction following, precise edits, composing from multiple references |
| Provenance | Invisible Content Seal watermark |
| Where Meta offers it | Meta AI app, meta.ai, Instagram Stories (US), WhatsApp (some countries) |
| On Kenerate | Meta Muse Image — 3.3 credits, 9 ratios, up to 10 references |
Gallery
Real outputs made on Kenerate. Open any image to copy its prompt and run it yourself.
Models
Every version in the generator, and what each is good at.
| Model | Reference images | Max size | Good for | Open |
|---|---|---|---|---|
| Meta Muse ImageMeta | Up to 10 | 9 ratios | Cheap multi-reference model | Open |
From our tests
This model runs through its provider with its own content rules. For adult art, use open models on the uncensored AI image generator (18+).
How to
Try Meta Muse Image on your own prompt — 25 free credits on sign-up.
In depth
Background, how to prompt it, and when to pick something else.
Most models that combine many references cost 14–27 credits. Muse Image does it for 3.3, which makes it a good way to try combines before re-running the best one on Seedream or GPT Image 2.
We only publish real, verified reviews — never invented quotes. Send a line about your result (and whether we may quote you), and it will appear here.
FAQ
4 questions
Meta's image model, announced on 7 July 2026 as the first image model from Meta Superintelligence Labs.
3.3 credits per image, with up to 10 reference images.
Meta embeds an invisible Content Seal watermark; Kenerate adds no visible watermark.
Meta says it composes from multiple references. On Kenerate it takes up to 10 reference images for 3.3 credits — one of the cheapest multi-reference models here.
Explore
Generators, design tools, photo edits, models and comparisons — all in one studio, on one credit balance.
Written by the Kenerate AI team
We run these models in the Kenerate generator. Model facts come from the makers' own pages; specs and limits were checked against our code; the examples are our own outputs. Last updated 27 September 2026. Corrections: hello@kenerateai.com.
Ready when you are
25 free credits on sign-up. No watermark.