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.
Muse Image
Glif default
Precise reference-based edits and fine details such as text, charts and QR codes.
Rated by blind team votes and an AI judge
As of
Score 78 · #1 of 15 in Character consistency
90% range 72–84
Score out of 100: how often people would pick this model's output over an average model's on the same tests. 50 is average.
How we score
On character consistency: Wins 53 / Losses 15 / Ties 13 from 81 team votes, plus 12 AI judge scores.
Every model runs the same Glif tests. Team members see two outputs side by side without the model names and pick the one that better fits the test, or call it a tie. An AI judge also scores every output from 0 to 10.
A Bradley-Terry fit turns all those head-to-head results into one rating per model. Ties count as half a win, and each AI judge score counts as half a vote.
The score is the predicted chance people prefer this model's output to the average model's on the same board, so 50 is average. A board is one kind of task, like text-to-image. Scores only compare models on the same board.
The 90% range comes from resampling the votes and refitting many times. Overlapping ranges are close to a tie. A model ranks once it has 20 votes' worth of ratings on a board. Until then it shows no score, only how close it is.
Other boards
Surgical image editing: 59 · #6 of 14
Brand and text rendering: 61 · #3 of 6
Text-to-image: 55 · #7 of 14
Product photography: 33 · #9 of 14
Image-to-image: Needs more ratings (19 of 20)
Multi-image reference: Needs more ratings (4 of 20)
Test outputs
Compare all modelsMuse Image in practice
What it does and when to use it.
Model summary
Muse Image is Meta’s image generation and editing model, served through fal. It accepts text prompts and reference images for tasks such as typography, plots, and targeted edits. Use it to develop visual concepts, designs with text, or new compositions from references.
Capabilities
Text to image
Image to image
Multi image reference
Text rendering
Suggested use cases
- Explore poster, logo, and infographic concepts
- Generate photos or illustrations from a written brief
- Make targeted edits using reference images