Wan 2.7 Imagevs.Kandinsky-5.0-T2I-Lite-Pretrain

Which one is better?

In our own test, Wan 2.7 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.

Wan 2.7 Image: Typography and layout, first image from the fixed test run — Wan 2.7 Image94 out of 100

Kandinsky-5.0-T2I-Lite-Pretrain: Typography and layout, first image from the fixed test run — Kandinsky-5.0-T2I-Lite-Pretrain16 out of 100

Result for “Typography and layout”:Wan 2.7 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

Wan 2.7 Image: fal, requested 1024x1024, n=1, seed=2030081785, estimated cost $0.030000, generated Nov 1, 2026, 9:22 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=893590444446603478; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE; native tokenizer truncation: CLIP 80 to 77 tokens; archived input unchanged, generated Nov 2, 2026, 8:56 PM. Source

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

Wan 2.7 Image image SHA 256: 62258e364ab7627aa6c1d0d4214ad1cc32287ede3b059aec041acf4dcdb20cf4

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: af9bdf8492b30fdaeb79b8f51d168a948d43ee1bbb29107f50a2f794db91a2e0

Infographic

Wan 2.7 Image: fal, requested 1024x1024, n=1, seed=1843752681, estimated cost $0.030000, generated Nov 1, 2026, 9:22 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=6008496123190594626; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE, generated Nov 2, 2026, 9:08 PM. Source

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

Wan 2.7 Image image SHA 256: f5707f29066b971a3c094495e0ff2a1bdd0479aa5c583a2a4d3b607ce7ca0636

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: 6d1a99203c55f6a9ba5853aae207dfc5e264adc73b336253fae874f0243bd60e

Product photography

Wan 2.7 Image: fal, requested 1024x1024, n=1, seed=1918862783, estimated cost $0.030000, generated Nov 1, 2026, 9:21 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=8854898730028115945; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE; native tokenizer truncation: CLIP 80 to 77 tokens; archived input unchanged, generated Nov 2, 2026, 8:46 PM. Source

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

Wan 2.7 Image image SHA 256: 6b7d5e90e75158d052d09c570b3af8fbb633ed1e20d9d84b8d23e864aeb446ac

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: 83169f5969d6ed636c5ba8ff01236290417a5942deec1089b4725cfeb0dc2b76

Typography and layout

Wan 2.7 Image: fal, requested 1024x1024, n=1, seed=457490918, estimated cost $0.030000, generated Nov 1, 2026, 9:21 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=9114026266664490789; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE, generated Nov 2, 2026, 8:36 PM. Source

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

Wan 2.7 Image image SHA 256: 60d9602757484b80c9a30506243d50d74d1160ff6998e80ba21aeb99338f5587

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: 89cd2a1137d4d2ceb46c44b030f889bb3b14ac96ae190d2eb271dff02cfb5b74

The numbers at a glance

Arena ratingfrom votes by users · higher is better

n/a

Wan 2.7 Image

not in the arena

n/a

Kandinsky-5.0-T2I-Lite-Pretrain

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better

Wan 2.7 Image

Rank 2 of 108

Kandinsky-5.0-T2I-Lite-Pretrain

Rank 86 of 108

Price per imagedollars through the API · lower is better

n/a

Wan 2.7 Image

no API price

n/a

Kandinsky-5.0-T2I-Lite-Pretrain

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.

Wan 2.7 Image

Subscription: At Alibaba from ≈ €6.36 a month (Token Plan Individual Lite, with limited credits). Through other providers from €6.83 a month (Poe Basic, with limited points). 12 plans in Germany.
Via API: No API price known. Access: API.
Weights: unknown.

Kandinsky-5.0-T2I-Lite-Pretrain

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	Wan 2.7 Image	Kandinsky-5.0-T2I-Lite-Pretrain
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	81	28
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition	94	16
Product photographyMaterials, reflections, and fine details	88	58
Character and detailAnatomy, clothing, and spatial consistency	63	14
InfographicNumbers, labels, and visual organization	79	23
API price
Per imagelower is better	n/a	n/a
100 images	n/a	n/a
Profile
Released	n/a	n/a
Weightsopen means: runs locally	unknown	open
Access	API	local
Parameters	not published	6 billion
Largest output	2K	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: Wan 2.7 Image model source (verified Nov 1, 2026) · Kandinsky-5.0-T2I-Lite-Pretrain 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 Wan 2.7 Image and Kandinsky-5.0-T2I-Lite-Pretrain from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare Wan 2.7 Image and Kandinsky-5.0-T2I-Lite-Pretrain with the models people compare them with most often.

Compare another matchup

First image modelSecond image model