Skip to main content

Kandinsky LabNVIDIA ResearchImage model matchup

Kandinsky-5.0-T2I-Lite-Pretrainvs.Sana-Sprint 1.6B 1024px

Which one is better?

In our own benchmark GraduallyBench Image v2, Kandinsky-5.0-T2I-Lite-Pretrain is slightly ahead, but not certainly. Neither is in the arena. Neither has an API price.

GraduallyBench Image v2Our own benchmark0 to 100 · higher is better
25

Kandinsky-5.0-T2I-Lite-Pretrain

Rank 90 of 108

12

Sana-Sprint 1.6B 1024px

Rank 101 of 108

Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench Image v2 run; prices compared with 28 models with an API price.

Test images from GraduallyBench Image v2

Our own benchmarkThe images come from GraduallyBench Image v2, our own benchmark: every model gets the same four tasks, and two AI judges compare the images in pairs and blind.

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

Kandinsky-5.0-T2I-Lite-Pretrain: Product photography, first image from the fixed test run
Kandinsky-5.0-T2I-Lite-Pretrain51 out of 100
Sana-Sprint 1.6B 1024px: Product photography, first image from the fixed test run
Sana-Sprint 1.6B 1024px12 out of 100

Result for “Product photography”:Kandinsky-5.0-T2I-Lite-Pretrain ahead

Prompt given to both modelsCreate a square premium product photograph of a brushed titanium wristwatch standing upright on dark green marble. The watch has a cream dial, thin black hands set to 10:10, twelve distinct hour markers, a realistic crown, and a dark brown leather strap. Soft window light from the left, controlled reflections, shallow depth of field, no text, no logo, no extra objects.

What the rating looks at: Materials, reflections, and fine details.

“Ahead”: the 95 % ranges of both values do not overlap. “Slightly ahead”: a higher value, but the ranges overlap.

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

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

Sana-Sprint 1.6B 1024px: manual, 1:1, one request, first output, one image, provider-side randomize seed enabled, observed seed 889651570, native 1024x1024, 2 inference steps, guidance 4.5, no prompt enhancement, no reference images, exact checkpoint Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers, Space commit b42328123ed688df4bee46e52c60cc1dc62c045a, generated Nov 1, 2026, 9:42 PM. Source

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

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

Sana-Sprint 1.6B 1024px image SHA 256: 1d77cacabeb38205299446bc6c5b80f38cf757d98f4251fc44c25340ab870dd9

Infographic

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

Sana-Sprint 1.6B 1024px: manual, 1:1, one request, first output, one image, provider-side randomize seed enabled, observed seed 853526908, native 1024x1024, 2 inference steps, guidance 4.5, no prompt enhancement, no reference images, exact checkpoint Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers, Space commit b42328123ed688df4bee46e52c60cc1dc62c045a; an earlier request on 2026-11-01 was rejected before generation by the ZeroGPU quota, generated Nov 2, 2026, 2:30 PM. Source

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

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

Sana-Sprint 1.6B 1024px image SHA 256: da4ed66ab2f25ea33c81978bc687142d50f7f7d01db096169151e70f1648ec43

Product photography

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

Sana-Sprint 1.6B 1024px: manual, 1:1, one request, first output, one image, provider-side randomize seed enabled, observed seed 178858232, native 1024x1024, 2 inference steps, guidance 4.5, no prompt enhancement, no reference images, exact checkpoint Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers, Space commit b42328123ed688df4bee46e52c60cc1dc62c045a, generated Nov 1, 2026, 9:42 PM. Source

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

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

Sana-Sprint 1.6B 1024px image SHA 256: 39284e75f1ffa7a286c193927441bca1bee31495f6cf67b4fd024a567a548b09

Typography and layout

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

Sana-Sprint 1.6B 1024px: manual, 1:1, one request, first output, one image, provider-side randomize seed enabled, observed seed 37807657, native 1024x1024, 2 inference steps, guidance 4.5, no prompt enhancement, no reference images, exact checkpoint Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers, Space commit b42328123ed688df4bee46e52c60cc1dc62c045a, generated Nov 1, 2026, 9:42 PM. Source

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

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

Sana-Sprint 1.6B 1024px image SHA 256: 5f4459e7adbe7d47fe3ba162ce8e13507b5ea6e3bb4beb5084c862df9ab9e933

Subscription and API

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).
Weights
Open weights.

Sana-Sprint 1.6B 1024px

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known (access: local).
Weights
Open weights.

Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.

GraduallyBench Image v2 from Nov 7, 2026 · Subscription database from Sep 29, 2026 (49 days old)

All data side by side

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

KennzahlKandinsky-5.0-T2I-Lite-PretrainSana-Sprint 1.6B 1024px
Ratings
Arena ratingfrom votes by users, higher is bettern/an/a
Arena rankn/an/a
Arena votesmore votes, a safer ratingn/an/a
GraduallyBench Image v2our own benchmark, 0 to 1002512
GraduallyBench Image v2 by task
Typography and layoutLegible text, hierarchy, and composition916
Product photographyMaterials, reflections, and fine details5112
Character and detailAnatomy, clothing, and spatial consistency1215
InfographicNumbers, labels, and visual organization263
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
Releasedn/aMar 22, 2025
Weightsopen means: runs locallyopenopen
Accesslocallocal
Parameters6 billion1.6 billion
Largest outputnot consistently publishednot consistently published
Plans in Germanynaming exactly this modeln/an/a

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

Sources: Kandinsky-5.0-T2I-Lite-Pretrain model source (verified Nov 1, 2026) · Sana-Sprint 1.6B 1024px model source (verified Nov 1, 2026)

Arena ratings by category

From blind votes on Artificial Analysis and LMArena; the sources are named under the card. “Ahead” means the lead is clear.

No shared arena score in the stored snapshot

The stored benchmark database contains no measurement for Kandinsky-5.0-T2I-Lite-Pretrain and Sana-Sprint 1.6B 1024px from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare another matchup