SenseNova U1.5 Litevs.Luma Uni-1.1
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.
Result for “Typography and layout”:SenseNova U1.5 Lite ahead
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
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
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
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
Protocol gradually-image-comparison-v1. Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6
SenseNova U1.5 Lite image SHA 256: c092b333f479c5b28ad33958d0e45f0fb0989970af02690079cf1398742c55b8
Luma Uni-1.1 image SHA 256: 4210462a5210fcde39e1f78167cb160cd3966176012d0ef2c187c6490d6a47e4
Infographic
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
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
Protocol gradually-image-comparison-v1. Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f
SenseNova U1.5 Lite image SHA 256: dcf8206386da05d11c35a6950309e61f08a504d440366226eac316328718f5ae
Luma Uni-1.1 image SHA 256: fef94f2000cb22c90b2a147753ace395ee6c14f3e803e0cc88376556dd5267bc
Product photography
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
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
Protocol gradually-image-comparison-v1. Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3
SenseNova U1.5 Lite image SHA 256: d425ed5236325ee28633f83cb00f3fd39181f7dd6df0e5408d8b1c07c6796107
Luma Uni-1.1 image SHA 256: 9e31a8397f6dd1f0a09a0440510edcdbfbac5470f75a78ec6c6b67783099e5c2
Typography and layout
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
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
Protocol gradually-image-comparison-v1. Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419
SenseNova U1.5 Lite image SHA 256: df5c50fc54f03b972796f424999bd5991ff758a6b7abc00c212864aca3b124bc
Luma Uni-1.1 image SHA 256: 97710d52e2207b2bf7db070cf1dfa54af5ce79fd7a1fec12bdb1616c648c01f4
The numbers at a glance
SenseNova U1.5 Lite
not in the arena
Luma Uni-1.1
not in the arena
SenseNova U1.5 Lite
Rank 14 of 108
Luma Uni-1.1
Rank 33 of 108
SenseNova U1.5 Lite
no API price
Luma Uni-1.1
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.
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.
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.
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 | SenseNova U1.5 Lite | Luma Uni-1.1 |
|---|---|---|
| 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 | 73 | 66 |
| GraduallyBench by task | ||
| Typography and layoutLegible text, hierarchy, and composition | 93 | 67 |
| Product photographyMaterials, reflections, and fine details | 84 | 60 |
| Character and detailAnatomy, clothing, and spatial consistency | 35 | 49 |
| InfographicNumbers, labels, and visual organization | 80 | 89 |
| API price | ||
| Per imagelower is better | n/a | n/a |
| 100 images | n/a | n/a |
| Profile | ||
| Released | n/a | May 11, 2026 |
| Weightsopen means: runs locally | open | unknown |
| Access | API, Web app, local | API |
| Parameters | not published | not published |
| Largest output | 4K | not consistently published |
| Plans in Germanynaming exactly this model | n/a | 6 |
API prices for one image at 1,024 × 1,024 pixels according to Artificial Analysis.
Sources: SenseNova U1.5 Lite model source (verified Nov 2, 2026) · Luma Uni-1.1 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 SenseNova U1.5 Lite and Luma Uni-1.1 from the same arena and category. Older model versions are not used as substitutes.
More comparisons
Compare SenseNova U1.5 Lite and Luma Uni-1.1 with the models people compare them with most often.