Luma Uni-1.1 Maxvs.SenseNova U1.5 Lite

Which one is better?

In our own test both are on par. Neither is in the arena. Neither has an API price.

Test images

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

Luma Uni-1.1 Max: Character and detail, first image from the fixed test run — Luma Uni-1.1 Max60 out of 100

SenseNova U1.5 Lite: Character and detail, first image from the fixed test run — SenseNova U1.5 Lite35 out of 100

Result for “Character and detail”:Luma Uni-1.1 Max slightly ahead

Prompt given to both modelsCreate a square cinematic full-body portrait of a fictional bicycle courier waiting under a transparent umbrella at a rainy tram stop in Hamburg at blue hour. She wears a mustard raincoat, navy trousers, red sneakers, a silver helmet, and carries a teal messenger bag. Keep both hands visible, render the bicycle correctly, use realistic wet-street reflections, and include no readable brand names.

What the rating looks at: Anatomy, clothing, and spatial consistency.

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

Test protocol of the images

Each test attempt uses the same archived prompt and one request. The first output of that attempt counts. Repeats after technical test failures are disclosed for the affected images. 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 Max: fal, aspect ratio 1:1, n=1, seed=provider random, estimated cost $0.102000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Aug 14, 2026, 1:47 PM. Source

SenseNova U1.5 Lite: manual, local stable-diffusion.cpp@3be23788fc0c9f35a2c24b1211caae11d4a54dbc, ggml@d49c49e1dd361ba3c0a77c90b5b1404b83969aa8; sensenova/SenseNova-U1.5-8B-MoT@9feeeab8a2792514d109cd34589342a2cc1d4ab2; native 2048x2048, 1:1; one request, first output; steps=50, guidance=4.0, seed=8087247682796819534; Apple M5 Max Metal MTL0 requested through the native backend option; automatic placement remains enabled, and actual placement is recorded in the CLI log; Original BF16 checkpoint. The exact two SenseNova vision convolution weights use a targeted lossless BF16-to-F32 rule; other eligible weights use the native unquantized f16 option. This BF16-to-F16 conversion rounds values, as quantified by the linked complete-checkpoint GGML preflight; excluded weights remain BF16 if used. Operation precision follows the backend.; Euler, flow shift 3; CPU Philox RNG (CLI cuda RNG option, no CUDA hardware); original BF16 weights without requested quantization; observational latent and pre-clipping finite checks; native prompt template without rewriting; empty unconditional prompt, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 10:17 PM. Source

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

Luma Uni-1.1 Max image SHA 256: 8034ca5627e1a256cdf1d06fc87b583d91d971d02edc9af7df52cd6721d3ea9c

SenseNova U1.5 Lite image SHA 256: c092b333f479c5b28ad33958d0e45f0fb0989970af02690079cf1398742c55b8

Infographic

Luma Uni-1.1 Max: fal, aspect ratio 1:1, n=1, seed=provider random, estimated cost $0.102000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Aug 14, 2026, 1:49 PM. Source

SenseNova U1.5 Lite: manual, local stable-diffusion.cpp@3be23788fc0c9f35a2c24b1211caae11d4a54dbc, ggml@d49c49e1dd361ba3c0a77c90b5b1404b83969aa8; sensenova/SenseNova-U1.5-8B-MoT@9feeeab8a2792514d109cd34589342a2cc1d4ab2; native 2048x2048, 1:1; one request, first output; steps=50, guidance=4.0, seed=2640628636372692680; Apple M5 Max Metal MTL0 requested through the native backend option; automatic placement remains enabled, and actual placement is recorded in the CLI log; Original BF16 checkpoint. The exact two SenseNova vision convolution weights use a targeted lossless BF16-to-F32 rule; other eligible weights use the native unquantized f16 option. This BF16-to-F16 conversion rounds values, as quantified by the linked complete-checkpoint GGML preflight; excluded weights remain BF16 if used. Operation precision follows the backend.; Euler, flow shift 3; CPU Philox RNG (CLI cuda RNG option, no CUDA hardware); original BF16 weights without requested quantization; observational latent and pre-clipping finite checks; native prompt template without rewriting; empty unconditional prompt, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 10:25 PM. Source

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

Luma Uni-1.1 Max image SHA 256: 36dea214eb680804d4fea089eec3d4f10a4bf7b7a71c7a80f92313a37e8c2f73

SenseNova U1.5 Lite image SHA 256: dcf8206386da05d11c35a6950309e61f08a504d440366226eac316328718f5ae

Product photography

Luma Uni-1.1 Max: fal, aspect ratio 1:1, n=1, seed=provider random, estimated cost $0.102000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Aug 14, 2026, 1:43 PM. Source

SenseNova U1.5 Lite: manual, local stable-diffusion.cpp@3be23788fc0c9f35a2c24b1211caae11d4a54dbc, ggml@d49c49e1dd361ba3c0a77c90b5b1404b83969aa8; sensenova/SenseNova-U1.5-8B-MoT@9feeeab8a2792514d109cd34589342a2cc1d4ab2; native 2048x2048, 1:1; one request, first output; steps=50, guidance=4.0, seed=1950293105094404455; Apple M5 Max Metal MTL0 requested through the native backend option; automatic placement remains enabled, and actual placement is recorded in the CLI log; Original BF16 checkpoint. The exact two SenseNova vision convolution weights use a targeted lossless BF16-to-F32 rule; other eligible weights use the native unquantized f16 option. This BF16-to-F16 conversion rounds values, as quantified by the linked complete-checkpoint GGML preflight; excluded weights remain BF16 if used. Operation precision follows the backend.; Euler, flow shift 3; CPU Philox RNG (CLI cuda RNG option, no CUDA hardware); original BF16 weights without requested quantization; observational latent and pre-clipping finite checks; native prompt template without rewriting; empty unconditional prompt, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 10:11 PM. Source

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

Luma Uni-1.1 Max image SHA 256: 4890cdf8b858c5740124e3b2ba038b73f6a35decc7e3e3d920890462b6e89c2b

SenseNova U1.5 Lite image SHA 256: d425ed5236325ee28633f83cb00f3fd39181f7dd6df0e5408d8b1c07c6796107

Typography and layout

Luma Uni-1.1 Max: fal, aspect ratio 1:1, n=1, seed=provider random, estimated cost $0.102000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Aug 14, 2026, 2:40 PM. Source

SenseNova U1.5 Lite: manual, local stable-diffusion.cpp@3be23788fc0c9f35a2c24b1211caae11d4a54dbc, ggml@d49c49e1dd361ba3c0a77c90b5b1404b83969aa8; sensenova/SenseNova-U1.5-8B-MoT@9feeeab8a2792514d109cd34589342a2cc1d4ab2; native 2048x2048, 1:1; one request, first output; steps=50, guidance=4.0, seed=8328647217678382438; Apple M5 Max Metal MTL0 requested through the native backend option; automatic placement remains enabled, and actual placement is recorded in the CLI log; Original BF16 checkpoint. The exact two SenseNova vision convolution weights use a targeted lossless BF16-to-F32 rule; other eligible weights use the native unquantized f16 option. This BF16-to-F16 conversion rounds values, as quantified by the linked complete-checkpoint GGML preflight; excluded weights remain BF16 if used. Operation precision follows the backend.; Euler, flow shift 3; CPU Philox RNG (CLI cuda RNG option, no CUDA hardware); original BF16 weights without requested quantization; observational latent and pre-clipping finite checks; native prompt template without rewriting; empty unconditional prompt; three local execution attempts: original Metal BF16 attempt aborted on a missing matrix kernel before output; same-seed CPU retry deliberately interrupted before its first sampling step without image or latent; first image retained after the reviewed loader compatibility correction and disclosed F16 runtime conversion with unchanged prompt and seed, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 10:04 PM. Source

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

Luma Uni-1.1 Max image SHA 256: d2a6162d544def0a283ed62f939b33252636d296a21142111851ecdedd2989d3

SenseNova U1.5 Lite image SHA 256: df5c50fc54f03b972796f424999bd5991ff758a6b7abc00c212864aca3b124bc

The numbers at a glance

Arena ratingfrom votes by users · higher is better

n/a

Luma Uni-1.1 Max

not in the arena

n/a

SenseNova U1.5 Lite

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better

Luma Uni-1.1 Max

Rank 20 of 108

SenseNova U1.5 Lite

Rank 14 of 108

Price per imagedollars through the API · lower is better

n/a

Luma Uni-1.1 Max

no API price

n/a

SenseNova U1.5 Lite

no API price

Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench run; prices compared with 28 models with an API price.

Luma Uni-1.1 Max

Subscription: n/a No plan in Germany names exactly this model.
Via API: No API price known. Access: API, Web app.

SenseNova U1.5 Lite

Subscription: n/a No plan in Germany names exactly this model.
Via API: No API price known. Access: API, Web app, 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 3, 2026 · Subscription database from Sep 29, 2026 (38 days old)

All data side by side

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

Kennzahl	Luma Uni-1.1 Max	SenseNova U1.5 Lite
Ratings
Arena ratingfrom votes by users, higher is better	n/a	n/a
Arena rank	n/a	n/a
Arena votesmore votes, a safer rating	n/a	n/a
GraduallyBenchour own rating, 0 to 100	71	73
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition	75	93
Product photographyMaterials, reflections, and fine details	71	84
Character and detailAnatomy, clothing, and spatial consistency	60	35
InfographicNumbers, labels, and visual organization	79	80
API price
Per imagelower is better	n/a	n/a
100 images	n/a	n/a
Profile
Released	May 2026	n/a
Weightsopen means: runs locally	proprietary	open
Access	API, Web app	API, Web app, local
Parameters	not published	not published
Largest output	2K	4K
Plans in Germanynaming exactly this model	n/a	n/a

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

Sources: Luma Uni-1.1 Max model source (verified Aug 15, 2026) · SenseNova U1.5 Lite model source (verified Nov 2, 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 Max and SenseNova U1.5 Lite from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare Luma Uni-1.1 Max and SenseNova U1.5 Lite with the models people compare them with most often.

Compare another matchup

First image modelSecond image model