Kandinsky-5.0-T2I-Lite-SFTvs.SANA-1.5 1.6B 1024px

Which one is better?

In our own test, Kandinsky-5.0-T2I-Lite-SFT 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.

Kandinsky-5.0-T2I-Lite-SFT: Character and detail, first image from the fixed test run — Kandinsky-5.0-T2I-Lite-SFT65 out of 100

SANA-1.5 1.6B 1024px: Character and detail, first image from the fixed test run — SANA-1.5 1.6B 1024px4 out of 100

Result for “Character and detail”:Kandinsky-5.0-T2I-Lite-SFT 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

SANA-1.5 1.6B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_1.6B_1024px_diffusers@b77948f2b4eed5c728e9b828ccff07f7427b43cc; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=4913908686846438154; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled, generated Nov 2, 2026, 5:32 PM. Source

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

Kandinsky-5.0-T2I-Lite-SFT image SHA 256: 8d193e702ad1aa0fccdb45f5d1474d60e21d455fa58d13470edd2796af0f2aed

SANA-1.5 1.6B 1024px image SHA 256: abc8d1fcb514ea7754211b79030abbf92ef83a61e546f19b217ccb06df0aaf45

Infographic

SANA-1.5 1.6B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_1.6B_1024px_diffusers@b77948f2b4eed5c728e9b828ccff07f7427b43cc; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=1936313402304398258; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled, generated Nov 2, 2026, 5:33 PM. Source

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

Kandinsky-5.0-T2I-Lite-SFT image SHA 256: e102016732db9e8e463504a83ac0770ff8a3c4c77918143d0f9dae8498c79101

SANA-1.5 1.6B 1024px image SHA 256: 828815adaab125d67312b64061f9b5a448558e9ac56ec9aa5ce8cf00cb63c481

Product photography

Kandinsky-5.0-T2I-Lite-SFT: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers@c0158b5b20858d1fc02088db7ed4d805a296498b; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=4636200764941689006; 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, 8:02 PM. Source

SANA-1.5 1.6B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_1.6B_1024px_diffusers@b77948f2b4eed5c728e9b828ccff07f7427b43cc; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=1353667313865032696; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled, generated Nov 2, 2026, 5:32 PM. Source

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

Kandinsky-5.0-T2I-Lite-SFT image SHA 256: 73b31dc5a48059f7712c6a125ac4855f2401133101172c4bfbaa11b76c5ceee1

SANA-1.5 1.6B 1024px image SHA 256: a43c512ad071c0d7526e16f69874b653f073c532403114299c8fde43770a72c8

Typography and layout

Kandinsky-5.0-T2I-Lite-SFT: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers@c0158b5b20858d1fc02088db7ed4d805a296498b; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=378697477899808767; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE; three local execution attempts: first aborted on an MPS dtype error; second returned an unsaved latent but the runner read the wrong output field; accepted first saved image after correcting that field with unchanged prompt, seed and FP32 sampling settings; lost latent content remains unknown, generated Nov 2, 2026, 7:52 PM. Source

SANA-1.5 1.6B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_1.6B_1024px_diffusers@b77948f2b4eed5c728e9b828ccff07f7427b43cc; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=2028788407160516328; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled; two submissions: first attempt produced no image after a documented MPS VAE decoding crash; technical repeat kept the same prompt and seed, generated Nov 2, 2026, 5:31 PM. Source

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

Kandinsky-5.0-T2I-Lite-SFT image SHA 256: a84280dd219692f7b20722a37491d6788d1ecdc594f816fa1203981642501ab2

SANA-1.5 1.6B 1024px image SHA 256: 7c58a1c863d5b8d22d06ed159b89aa64d13cf9a44f7b3d4871683f491f0bb75c

The numbers at a glance

Arena ratingfrom votes by users · higher is better

n/a

Kandinsky-5.0-T2I-Lite-SFT

not in the arena

n/a

SANA-1.5 1.6B 1024px

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better

Kandinsky-5.0-T2I-Lite-SFT

Rank 79 of 108

SANA-1.5 1.6B 1024px

Rank 107 of 108

Price per imagedollars through the API · lower is better

n/a

Kandinsky-5.0-T2I-Lite-SFT

no API price

n/a

SANA-1.5 1.6B 1024px

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.

Kandinsky-5.0-T2I-Lite-SFT

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

SANA-1.5 1.6B 1024px

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	Kandinsky-5.0-T2I-Lite-SFT	SANA-1.5 1.6B 1024px
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	34	4
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition	21	3
Product photographyMaterials, reflections, and fine details	15	0
Character and detailAnatomy, clothing, and spatial consistency	65	4
InfographicNumbers, labels, and visual organization	33	7
API price
Per imagelower is better	n/a	n/a
100 images	n/a	n/a
Profile
Released	n/a	Mar 16, 2025
Weightsopen means: runs locally	open	open
Access	local	local
Parameters	6 billion	1.6 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: Kandinsky-5.0-T2I-Lite-SFT model source (verified Nov 1, 2026) · SANA-1.5 1.6B 1024px 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 Kandinsky-5.0-T2I-Lite-SFT and SANA-1.5 1.6B 1024px from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare Kandinsky-5.0-T2I-Lite-SFT and SANA-1.5 1.6B 1024px with the models people compare them with most often.

Compare another matchup

First image modelSecond image model