Skip to main content

Luma Uni-1.1vs.MOSS-Image-SFT

Which one is better?

In our own test, Luma Uni-1.1 leads. Neither is in the arena. Neither has an API price.

Same prompt, two images

Same task, the first image of each. The task with the biggest difference is preselected.

Luma Uni-1.1: Typography and layout, first image from the fixed test run
Luma Uni-1.164 out of 100
MOSS-Image-SFT: Typography and layout, first image from the fixed test run
MOSS-Image-SFT13 out of 100

Result for “Typography and layout”:Luma Uni-1.1 ahead

Prompt given to both modelsCreate a square editorial poster for an imaginary night train called MONDFALTER. Show the exact German headline MONDFALTER and the exact subline BERLIN NACH LISSABON. Use a restrained midnight-blue and warm-cream palette, one stylized moth, strong Swiss-grid typography, generous negative space, and no additional words or logos.

What the rating looks at: Legible text, hierarchy, and composition.

“Ahead”: better in all three rating rounds. “Slightly ahead”: a higher value, but not in every round.

Test protocol of the images

Both models receive the same archived prompt in exactly one request, and the first result counts. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier and prompt processing can still differ. The images are a practical visual test, not a reconstruction of the arena configuration.

Character and detail

Luma Uni-1.1: fal, aspect ratio 1:1, n=1, seed=provider random, Fal schema does not expose an output-resolution parameter; require square output of at least 1024px, estimated cost $0.042000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 8:49 PM. Source

MOSS-Image-SFT: fal, requested 1024x1024, n=1, seed=2105639597, prompt expansion disabled, estimated charge ceiling $0.055, Fal lists $0.05 per MP, estimated cost $0.055000, generated Nov 1, 2026, 8:45 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

Luma Uni-1.1 image SHA 256: 4210462a5210fcde39e1f78167cb160cd3966176012d0ef2c187c6490d6a47e4

MOSS-Image-SFT image SHA 256: 772013206361c55e807d5004620682a603061ffbabb0cb28e24993a18c0a4ad5

Infographic

Luma Uni-1.1: fal, aspect ratio 1:1, n=1, seed=provider random, Fal schema does not expose an output-resolution parameter; require square output of at least 1024px, estimated cost $0.042000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 8:50 PM. Source

MOSS-Image-SFT: fal, requested 1024x1024, n=1, seed=454165776, prompt expansion disabled, estimated charge ceiling $0.055, Fal lists $0.05 per MP, estimated cost $0.055000, generated Nov 1, 2026, 8:45 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

Luma Uni-1.1 image SHA 256: fef94f2000cb22c90b2a147753ace395ee6c14f3e803e0cc88376556dd5267bc

MOSS-Image-SFT image SHA 256: f46b17df7becc603d27762b2d235128ffc30f5722f51e8d50cd6df4723409dd9

Product photography

Luma Uni-1.1: fal, aspect ratio 1:1, n=1, seed=provider random, Fal schema does not expose an output-resolution parameter; require square output of at least 1024px, estimated cost $0.042000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 8:47 PM. Source

MOSS-Image-SFT: fal, requested 1024x1024, n=1, seed=1064044164, prompt expansion disabled, estimated charge ceiling $0.055, Fal lists $0.05 per MP, estimated cost $0.055000, generated Nov 1, 2026, 8:45 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

Luma Uni-1.1 image SHA 256: 9e31a8397f6dd1f0a09a0440510edcdbfbac5470f75a78ec6c6b67783099e5c2

MOSS-Image-SFT image SHA 256: ae1015034efbde73cece799521a3a2e98ad82a8362eaf97f5bc1266e13386d57

Typography and layout

Luma Uni-1.1: fal, aspect ratio 1:1, n=1, seed=provider random, Fal schema does not expose an output-resolution parameter; require square output of at least 1024px, estimated cost $0.042000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 8:46 PM. Source

MOSS-Image-SFT: fal, requested 1024x1024, n=1, seed=1635014357, prompt expansion disabled, estimated charge ceiling $0.055, Fal lists $0.05 per MP, estimated cost $0.055000, generated Nov 1, 2026, 8:44 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

Luma Uni-1.1 image SHA 256: 97710d52e2207b2bf7db070cf1dfa54af5ce79fd7a1fec12bdb1616c648c01f4

MOSS-Image-SFT image SHA 256: 61feaf0c1af07a1cc8dd874c51dc8e86b5bfc271042b8e25f2512cb5a03ec51d

The numbers at a glance

Arena ratingfrom votes by users · higher is better
n/a

Luma Uni-1.1

not in the arena

n/a

MOSS-Image-SFT

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better
67

Luma Uni-1.1

Rank 14 of 74

41

MOSS-Image-SFT

Rank 52 of 74

Price per imagedollars through the API · lower is better
n/a

Luma Uni-1.1

no API price

n/a

MOSS-Image-SFT

no API price

Ranks among the 22 image models with an arena rating and the 74 with a GraduallyBench run; prices compared with 28 models with an API price.

Luma Uni-1.1

Subscription
No Luma AI subscription includes this model. Through other providers from €19.04 a month (Magnific Premium, with limited credits). 6 plans in Germany.
Via API
No API price known. Access: API.
Weights
unknown.

MOSS-Image-SFT

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known. Access: local.
License
Open weights.

Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.

GraduallyBench from Nov 1, 2026 · Subscription database from Sep 29, 2026 (34 days old)

All data side by side

The better value is bold. For ratings only when the gap is clear.

KennzahlLuma Uni-1.1MOSS-Image-SFT
Ratings
Arena ratingfrom votes by users, higher is bettern/an/a
Arena rankn/an/a
Arena votesmore votes, a safer ratingn/an/a
GraduallyBenchour own rating, 0 to 1006741
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition6413
Product photographyMaterials, reflections, and fine details5958
Character and detailAnatomy, clothing, and spatial consistency4817
InfographicNumbers, labels, and visual organization9575
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
ReleasedMay 11, 2026Oct 16, 2026
Weightsopen means: runs locallyunknownopen
AccessAPIlocal
Parametersnot published5 billion
Largest outputnot consistently publishednot consistently published
Plans in Germanynaming exactly this model6n/a

API prices for one image at 1,024 × 1,024 pixels according to Artificial Analysis.

Sources: Luma Uni-1.1 model source (verified Nov 1, 2026) · MOSS-Image-SFT model source (verified Nov 1, 2026)

Arena ratings by category

From blind votes on LMArena. “Ahead” means the lead is clear.

No shared arena score in the stored snapshot

The stored benchmark database contains no measurement for Luma Uni-1.1 and MOSS-Image-SFT from the same arena and category. Older model versions are not used as substitutes.

Compare another matchup

More matchups

Related image model comparisons

Compare Luma Uni-1.1 and MOSS-Image-SFT with other important image models.

View the complete image model comparison