LLaDA-Image-Turbovs.Lumina-Image 2.0

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.

LLaDA-Image-Turbo: Character and detail, first image from the fixed test run — LLaDA-Image-Turbo53 out of 100

Lumina-Image 2.0: Character and detail, first image from the fixed test run — Lumina-Image 2.023 out of 100

Result for “Character and detail”:LLaDA-Image-Turbo 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

LLaDA-Image-Turbo: manual, PyTorch 2.13.0, Diffusers 0.39.0, Transformers 4.57.6; inclusionAI/LLaDA-Image-Turbo@f4afc52d925bbac4e22a1c947111fc1f127e37e5; native 1024x1024, 1:1; one request per local attempt, first output; steps=4, guidance=1.0; seed=7961710876241130415; separate MPS initial-latent generator and global MPS scheduler RNG streams with the same integer seed; original Turbo scheduler, stochastic_sampling=true, uniform sigmas, shift=3; BF16 text encoder and diffusion components, FP32 denoising latent and CPU FP32 VAE decode; historical poster uses FP8 text encoder and remains unchanged; no CUDA equivalence claimed; MPS fallback permitted, actual fallback operations not measured, generated Nov 3, 2026, 9:54 AM. Source

Lumina-Image 2.0: fal, requested 1024x1024, n=1, seed=provider random, estimated cost $0.150000, generated Nov 1, 2026, 9:38 PM. Source

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

LLaDA-Image-Turbo image SHA 256: aac02152ef0efc45749b3d0a626e9f4114418394aeb6a92d492651c564f40fee

Lumina-Image 2.0 image SHA 256: 8747df0401d91598486735bfff5d6bac6c139727a8bc50c60bf7f697f678b85f

Infographic

LLaDA-Image-Turbo: manual, PyTorch 2.13.0, Diffusers 0.39.0, Transformers 4.57.6; inclusionAI/LLaDA-Image-Turbo@f4afc52d925bbac4e22a1c947111fc1f127e37e5; native 1024x1024, 1:1; one request per local attempt, first output; steps=4, guidance=1.0; seed=5156250474893981751; separate MPS initial-latent generator and global MPS scheduler RNG streams with the same integer seed; original Turbo scheduler, stochastic_sampling=true, uniform sigmas, shift=3; BF16 text encoder and diffusion components, FP32 denoising latent and CPU FP32 VAE decode; historical poster uses FP8 text encoder and remains unchanged; no CUDA equivalence claimed; MPS fallback permitted, actual fallback operations not measured, generated Nov 3, 2026, 9:56 AM. Source

Lumina-Image 2.0: fal, requested 1024x1024, n=1, seed=provider random, estimated cost $0.150000, generated Nov 1, 2026, 9:38 PM. Source

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

LLaDA-Image-Turbo image SHA 256: 4e8939998310be86b1ad3dc0744a5e3ceee95a00a9113ee6732f9c06cb6b3618

Lumina-Image 2.0 image SHA 256: b937b28f3c3209280c5828e18c85341d3ca443175020ca1e407dae035b5df14f

Product photography

LLaDA-Image-Turbo: manual, PyTorch 2.13.0, Diffusers 0.39.0, Transformers 4.57.6; inclusionAI/LLaDA-Image-Turbo@f4afc52d925bbac4e22a1c947111fc1f127e37e5; native 1024x1024, 1:1; one request per local attempt, first output; steps=4, guidance=1.0; seed=0; separate MPS initial-latent generator and global MPS scheduler RNG streams with the same integer seed; original Turbo scheduler, stochastic_sampling=true, uniform sigmas, shift=3; BF16 text encoder and diffusion components, FP32 denoising latent and CPU FP32 VAE decode; historical poster uses FP8 text encoder and remains unchanged; no CUDA equivalence claimed; MPS fallback permitted, actual fallback operations not measured; historical Hugging Face Space product-photo attempt used the same archived prompt and seed 0 but a different request body and backend; its AppError left the output unresolved; this is not an exact request replay or a numerical-equivalence comparison, generated Nov 3, 2026, 9:48 AM. Source

Lumina-Image 2.0: fal, requested 1024x1024, n=1, seed=provider random, estimated cost $0.150000, generated Nov 1, 2026, 9:38 PM. Source

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

LLaDA-Image-Turbo image SHA 256: e61fb35e0c12941d28d32b0e0125b934bc0857fc49216a7945406e3bf58b4316

Lumina-Image 2.0 image SHA 256: 74b79fcbad7565e29995c941d2b488d2edde884b307ed99e47fad994424e9dfc

Typography and layout

LLaDA-Image-Turbo: manual, 1:1, native 1024x1024, one request in the successful technical repeat, first output; two total submissions after a local download failure; seed 0 (fixed provider default, randomize_seed=false); BF16 transformer, FP8 text encoder; 4 steps, CFG 1.0; HF Space commit 7b02431121944d65b8065873b48eec736a0c1022; source PNG SHA-256 d1866b4994a664728de07f1c1897776bbf04409b4a00ad7fa98666036a78816d, generated Nov 2, 2026, 3:03 PM. Source

Lumina-Image 2.0: fal, requested 1024x1024, n=1, seed=provider random, estimated cost $0.150000, generated Nov 1, 2026, 9:37 PM. Source

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

LLaDA-Image-Turbo image SHA 256: de0c780506575a32050ce9ca3d3c4dd1a0c4cc7ccf7f7f2f6aaf17ad01295901

Lumina-Image 2.0 image SHA 256: f132c159d659fb76c94cd82f1decb617c475b9c4095b177d02b73f09f2954df0

The numbers at a glance

Arena ratingfrom votes by users · higher is better

n/a

LLaDA-Image-Turbo

not in the arena

n/a

Lumina-Image 2.0

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better

LLaDA-Image-Turbo

Rank 83 of 108

Lumina-Image 2.0

Rank 97 of 108

Price per imagedollars through the API · lower is better

n/a

LLaDA-Image-Turbo

no API price

n/a

Lumina-Image 2.0

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.

LLaDA-Image-Turbo

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

Lumina-Image 2.0

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	LLaDA-Image-Turbo	Lumina-Image 2.0
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	18
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition	8	18
Product photographyMaterials, reflections, and fine details	27	16
Character and detailAnatomy, clothing, and spatial consistency	53	23
InfographicNumbers, labels, and visual organization	36	16
API price
Per imagelower is better	n/a	n/a
100 images	n/a	n/a
Profile
Released	Sep 4, 2026	Jan 25, 2025
Weightsopen means: runs locally	open	open
Access	local	local
Parameters	6 billion	2.6 billion
Largest output	not consistently published	not consistently published
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: LLaDA-Image-Turbo model source (verified Nov 1, 2026) · Lumina-Image 2.0 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 LLaDA-Image-Turbo and Lumina-Image 2.0 from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare LLaDA-Image-Turbo and Lumina-Image 2.0 with the models people compare them with most often.

Compare another matchup

First image modelSecond image model