FLUX1.1 [pro] Ultravs.LLaDA-Image

Which one is better?

In our own test, LLaDA-Image leads. 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.

FLUX1.1 [pro] Ultra: Typography and layout, first image from the fixed test run — FLUX1.1 [pro] Ultra22 out of 100

LLaDA-Image: Typography and layout, first image from the fixed test run — LLaDA-Image62 out of 100

Result for “Typography and layout”:LLaDA-Image 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

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

FLUX1.1 [pro] Ultra: fal, aspect ratio 1:1; provider-native resolution, n=1, seed=3831910390, Fal exposes no resolution input; endpoint supports output up to 2K, Prompt enhancement disabled with enhance_prompt=false; default safety tolerance 2, estimated cost $0.060000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 2:50 PM. Source

LLaDA-Image: manual, 2.13.0 PyTorch, Diffusers 0.39.0, Transformers 4.57.6; inclusionAI/LLaDA-Image@e4e2703f410f7ddb6ee8d6b09dac6a8ec5093039; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0; seed=6428048197886116697; MPS generator; BF16 text/diffusion components, FP32 denoising latent, receipt-reported CPU FP32 native VAE decode; negative_prompt argument omitted (None default, not the manufacturer's empty-string example); MPS community PR @ 5395ce055da9975b09f71e21b865973d409bb3cd; official pinned text encoder uses eager MoE fallback and SDPA attention; other image-component attention paths were not independently captured by this review; no CUDA numerical equivalence claimed; MPS fallback permitted, actual fallback operations not measured; two submissions: the original request stopped at the 60-GiB free-space safeguard before image or latent (supervisor exit 143); one technical same-request/same-seed retry produced the retained first completed output; no quality reroll, generated Nov 3, 2026, 8:50 AM. Source

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

FLUX1.1 [pro] Ultra image SHA 256: 0b97e1e3f33be2844c06cc18618fea633273ada7e9d6404f9769cdb8403ffbfc

LLaDA-Image image SHA 256: a34d96894f5500c5bce2c16cca14ae09748f3aff4d47d15f8aff0d1be5749211

Infographic

FLUX1.1 [pro] Ultra: fal, aspect ratio 1:1; provider-native resolution, n=1, seed=1664027293, Fal exposes no resolution input; endpoint supports output up to 2K, Prompt enhancement disabled with enhance_prompt=false; default safety tolerance 2, estimated cost $0.060000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 2:50 PM. Source

LLaDA-Image: manual, 2.13.0 PyTorch, Diffusers 0.39.0, Transformers 4.57.6; inclusionAI/LLaDA-Image@e4e2703f410f7ddb6ee8d6b09dac6a8ec5093039; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0; seed=1354677768900879717; MPS generator; BF16 text/diffusion components, FP32 denoising latent, receipt-reported CPU FP32 native VAE decode; negative_prompt argument omitted (None default, not the manufacturer's empty-string example); MPS community PR @ 5395ce055da9975b09f71e21b865973d409bb3cd; official pinned text encoder uses eager MoE fallback and SDPA attention; other image-component attention paths were not independently captured by this review; no CUDA numerical equivalence claimed; MPS fallback permitted, actual fallback operations not measured, generated Nov 3, 2026, 8:56 AM. Source

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

FLUX1.1 [pro] Ultra image SHA 256: 2c7d24fcda220cf5eff966e1b857f11ad0e561f81ac9e4106ef1b4bd71686637

LLaDA-Image image SHA 256: cad67ad3f1a475d12bc2152840dc98657f81b5c7318c09a9e9fa40fbb433372f

Product photography

FLUX1.1 [pro] Ultra: fal, aspect ratio 1:1; provider-native resolution, n=1, seed=291934417, Fal exposes no resolution input; endpoint supports output up to 2K, Prompt enhancement disabled with enhance_prompt=false; default safety tolerance 2, estimated cost $0.060000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 2:49 PM. Source

LLaDA-Image: manual, 2.13.0 PyTorch, Diffusers 0.39.0, Transformers 4.57.6; inclusionAI/LLaDA-Image@e4e2703f410f7ddb6ee8d6b09dac6a8ec5093039; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0; seed=152405017095880227; MPS generator; BF16 text/diffusion components, FP32 denoising latent, receipt-reported CPU FP32 native VAE decode; negative_prompt argument omitted (None default, not the manufacturer's empty-string example); MPS community PR @ 5395ce055da9975b09f71e21b865973d409bb3cd; official pinned text encoder uses eager MoE fallback and SDPA attention; other image-component attention paths were not independently captured by this review; no CUDA numerical equivalence claimed; MPS fallback permitted, actual fallback operations not measured, generated Nov 3, 2026, 1:02 AM. Source

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

FLUX1.1 [pro] Ultra image SHA 256: 7d497c35126a92de69af61e5721158a10f4e2acf88a8526dcdd0f8a9a571e028

LLaDA-Image image SHA 256: 888e173c25c26ff1dcbfd07aad01ffc6a71cc7735099d3e943e60dfddfe31553

Typography and layout

FLUX1.1 [pro] Ultra: fal, aspect ratio 1:1; provider-native resolution, n=1, seed=1909595532, Fal exposes no resolution input; endpoint supports output up to 2K, Prompt enhancement disabled with enhance_prompt=false; default safety tolerance 2, estimated cost $0.060000, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 2, 2026, 2:49 PM. Source

LLaDA-Image: manual, 2.13.0 PyTorch, Diffusers 0.39.0, Transformers 4.57.6; inclusionAI/LLaDA-Image@e4e2703f410f7ddb6ee8d6b09dac6a8ec5093039; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0; seed=8778315039365154420; MPS generator; BF16 text/diffusion components, FP32 denoising latent, receipt-reported CPU FP32 native VAE decode; negative_prompt argument omitted (None default, not the manufacturer's empty-string example); MPS community PR @ 5395ce055da9975b09f71e21b865973d409bb3cd; official pinned text encoder uses eager MoE fallback and SDPA attention; other image-component attention paths were not independently captured by this review; no CUDA numerical equivalence claimed; MPS fallback permitted, actual fallback operations not measured, generated Nov 3, 2026, 12:40 AM. Source

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

FLUX1.1 [pro] Ultra image SHA 256: 0dfeffb6c3489b9ac2e1ae9100793320fa4f5eab779269de7aff3a4b768595f3

LLaDA-Image image SHA 256: 256a88541c9821a6242bb434fb520d4d6f0793c934c66acd1fd2e8edd8086b5d

The numbers at a glance

Arena ratingfrom votes by users · higher is better

n/a

FLUX1.1 [pro] Ultra

not in the arena

n/a

LLaDA-Image

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better

FLUX1.1 [pro] Ultra

Rank 83 of 108

LLaDA-Image

Rank 63 of 108

Price per imagedollars through the API · lower is better

n/a

FLUX1.1 [pro] Ultra

no API price

n/a

LLaDA-Image

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.

FLUX1.1 [pro] Ultra

Subscription: No Black Forest Labs subscription includes this model. Through other providers from ≈ €9.54 a month (Krea Basic, with limited credits). 12 plans in Germany.
Via API: No API price known. Access: API.
Weights: unknown.

LLaDA-Image

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 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	FLUX1.1 [pro] Ultra	LLaDA-Image
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	31	48
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition	22	62
Product photographyMaterials, reflections, and fine details	28	35
Character and detailAnatomy, clothing, and spatial consistency	45	63
InfographicNumbers, labels, and visual organization	28	33
API price
Per imagelower is better	n/a	n/a
100 images	n/a	n/a
Profile
Released	n/a	Sep 4, 2026
Weightsopen means: runs locally	unknown	open
Lifecycle	Separate Ultra API route / Ultra mode; no independent checkpoint established	no notice
Access	API	local
Parameters	not published	6 billion
Largest output	not consistently published	not consistently published
Plans in Germanynaming exactly this model	12	n/a

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

Sources: FLUX1.1 [pro] Ultra model source, status source (verified Nov 1, 2026) · LLaDA-Image 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 FLUX1.1 [pro] Ultra and LLaDA-Image from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare FLUX1.1 [pro] Ultra and LLaDA-Image with the models people compare them with most often.

Compare another matchup

First image modelSecond image model