SANA-1.5 1.6B 1024pxvs.Z-Image Base

Which one is better?

In our own test, Z-Image Base 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.

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

Z-Image Base: Character and detail, first image from the fixed test run — Z-Image Base71 out of 100

Result for “Character and detail”:Z-Image Base 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

Z-Image Base: fal, requested 1024x1024, n=1, seed=1788591829, estimated cost $0.020000, generated Nov 1, 2026, 9:35 PM. Source

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

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

Z-Image Base image SHA 256: 7a9c8b160230e302e618ad99ed1047d36b66bdc759d8455d0479048c442cdf75

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

Z-Image Base: fal, requested 1024x1024, n=1, seed=2013338091, estimated cost $0.020000, generated Nov 1, 2026, 9:35 PM. Source

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

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

Z-Image Base image SHA 256: b306143deb4d133e60ff4840e5fb8271d445f5a4944b98e89346763d84a19d30

Product photography

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

Z-Image Base: fal, requested 1024x1024, n=1, seed=1140297503, estimated cost $0.020000, generated Nov 1, 2026, 9:35 PM. Source

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

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

Z-Image Base image SHA 256: 11b631f154a0ddff86df21d6d8ffab0d208d51df894f3563dd6818d20b450aae

Typography and layout

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

Z-Image Base: fal, requested 1024x1024, n=1, seed=194884257, estimated cost $0.010486, generated Nov 1, 2026, 9:20 PM. Source

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

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

Z-Image Base image SHA 256: 62dbb49a07e3efe0f82ae9051fac20fce00a8f82b57ebe37a526b5176523c84f

The numbers at a glance

Arena ratingfrom votes by users · higher is better

n/a

SANA-1.5 1.6B 1024px

not in the arena

n/a

Z-Image Base

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better

SANA-1.5 1.6B 1024px

Rank 107 of 108

Z-Image Base

Rank 74 of 108

Price per imagedollars through the API · lower is better

n/a

SANA-1.5 1.6B 1024px

no API price

n/a

Z-Image Base

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.

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.

Z-Image Base

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	SANA-1.5 1.6B 1024px	Z-Image Base
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	4	37
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition	3	33
Product photographyMaterials, reflections, and fine details	0	22
Character and detailAnatomy, clothing, and spatial consistency	4	71
InfographicNumbers, labels, and visual organization	7	24
API price
Per imagelower is better	n/a	n/a
100 images	n/a	n/a
Profile
Released	Mar 16, 2025	Jan 27, 2026
Weightsopen means: runs locally	open	open
Access	local	local
Parameters	1.6 billion	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: SANA-1.5 1.6B 1024px model source (verified Nov 1, 2026) · Z-Image Base 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 SANA-1.5 1.6B 1024px and Z-Image Base from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare SANA-1.5 1.6B 1024px and Z-Image Base with the models people compare them with most often.

Compare another matchup

First image modelSecond image model