muse-image logo

Muse Image

Glif default
Use this model

Precise reference-based edits and fine details such as text, charts and QR codes.

OutputsImage
SpeedMedium
Price1 credit
CostLow
LabMeta
ReleasedJul 2026

Glif score

As of

Overall 71 · Score 71 · #3 of 19 in Character consistency

Scores combine expert human reviewers, expert AI judges and votes from the wider community, and we rank models on quality, speed and cost. * Early score: needs more ratings.

Other boards

Test outputs

Muse Image in practice

What it does and when to use it.

Model summary

Muse Image is Meta’s image generation and editing model. It works from a text prompt and up to 10 reference images, with nine aspect ratios from 21:9 to 9:21, or picks the shape itself when you leave the ratio unset. It follows instructions closely and renders fine details such as text, typography, plots and QR codes. Glif charges per image.

Capabilities

Text to image
Image to image
Multi image reference
Text rendering

Suggested use cases

  • Poster, logo and infographic concepts
  • Photos or illustrations from a written brief
  • Targeted edits guided by up to 10 reference images
  • Charts, plots and QR codes inside an image

All the models in one place

Run Muse Image and every other model on Glif from one chat. One account, one balance, no API keys to wire up.