Skip to main content

NVIDIA ResearchImage model

Sana-Sprint 1.6B 1024px

Sana-Sprint 1.6B 1024px is rank 96 of 108 in our GraduallyBench test.

Arena ratingnot rated

n/aUser voteshigher is better

GraduallyBenchRank 96 of 108

21our own rating0 to 100

Priceno price

n/aper imagelower is better

PopularityRank 670 of 875

0out of 100first value

Summary

Sana-Sprint 1.6B 1024px is an image model from NVIDIA Research. Sana-Sprint 1.6B is a distinct distilled speed checkpoint; the official example uses two steps, while the model card describes adaptive execution in one to four steps.

Image samples from our tests

These images come from documented single requests with an archived prompt. They complement measurements but do not replace a controlled laboratory test.

Character and detailOpen Character and detail at original size

Character and detail

This sample tests Anatomy, clothing, and spatial consistency.

Prompt and settings

Create 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.

Generated through manual. Archived settings were 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.

Open source
InfographicOpen Infographic at original size

Infographic

This sample tests Numbers, labels, and visual organization.

Prompt and settings

Create a square German infographic titled SO FUNKTIONIERT PHOTOSYNTHESE. Show exactly four numbered steps in this order: 1 LICHT, 2 WASSER, 3 CO₂, 4 ZUCKER + SAUERSTOFF. Use a clean editorial science style with one plant cross-section, simple arrows, high contrast, legible labels, and no other text.

Generated through manual. Archived settings were 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.

Open source
Product photographyOpen Product photography at original size

Product photography

This sample tests Materials, reflections, and fine details.

Prompt and settings

Create 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.

Generated through manual. Archived settings were 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.

Open source
Typography and layoutOpen Typography and layout at original size

Typography and layout

This sample tests Legible text, hierarchy, and composition.

Prompt and settings

Create 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.

Generated through manual. Archived settings were 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.

Open source

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 4 published benchmark results

Published benchmarks

Gradually sample test: Typography and layout

The 0-100 value normalizes the mean rank from model-blind comparison rounds. One archived first output contributes per model. This remains an n = 1 sample.

Nano Banana 299.7 rank points
FLUX.2 Flex98.1 rank points
FLUX 3 Image96 rank points
Recraft V4.1 Utility95.6 rank points
Wan 2.7 Image94.1 rank points
SenseNova U1.5 Lite93.1 rank points
Kling Image 3.0 Omni92.8 rank points
Nano Banana Pro91.9 rank points
FLUX.2 Max91.6 rank points
Recraft V4.1 Flash88.5 rank points
Krea 2 Large86.3 rank points
Firefly Image Model 585.7 rank points
Muse Image85.7 rank points
FLUX 3 Image Klein84.4 rank points
Seedream 4.583.8 rank points
MAI-Image-2.582.2 rank points
Nano Banana 2 Lite82.2 rank points
Qwen Image 2.0 Pro81 rank points
Wan 2.7 Image Pro81 rank points
Krea 377.6 rank points
Seedream 5.0 Flash76.6 rank points
HiDream-O1-Image-1.575.7 rank points
Seedream 5.0 Lite75.7 rank points
Luma Uni-1.1 Max75.1 rank points
GPT Image 274.5 rank points
Grok Imagine Image 1.073.8 rank points
Nano Banana 2.172.3 rank points
Krea 2 Medium Turbo71.3 rank points
Grok Imagine Image 2.070.7 rank points
MAI-Image-2.5 Flash70.1 rank points
Recraft V4.169.5 rank points
FLUX.2 Pro68.9 rank points
Bria FIBO 268.5 rank points
GPT Image 1 Mini67.9 rank points
Seedream 5.0 Pro67.9 rank points
Ideogram 4.067.3 rank points
Luma Uni-1.167 rank points
Seedream 4.064.8 rank points
GPT Image 2.5 Flare63.9 rank points
LLaDA-Image62 rank points
MAI-Image-2.662 rank points
GPT Image 1.559.5 rank points
FLUX.2 Klein 9B Preview55.8 rank points
Reve 2.153.9 rank points
GPT Image 2.5 Sunburst53.6 rank points
MAI-Image-2.6 Flash53.6 rank points
Qwen-Image-2.153.6 rank points
Kling Image 3.051.4 rank points
Runway Gen-4 Image51.4 rank points
MOSS-Image-Base50.8 rank points
Qwen Image 2.1 Turbo50.8 rank points
GLM-Image50.2 rank points
FLUX.2 Dev49.8 rank points
FLUX.1 Kontext [max]45.5 rank points
Hy Image 3.5 Preview45.2 rank points
FLUX1.1 [pro]42.1 rank points
LongCat-Image41.4 rank points
Wan 2.6 Text to Image41.1 rank points
Z-Image Turbo39.6 rank points
Nucleus-Image38.3 rank points
Qwen Image 2.1 Pro38.3 rank points
MiniMax Image-0137.4 rank points
Chroma1-HD36.4 rank points
Bria FIBO Lite35.5 rank points
Qwen Image 3.0 Pro35.5 rank points
Z-Image Base32.7 rank points
FLUX.2 Klein 9B32.4 rank points
Qwen Image 3.032.4 rank points
FLUX.2 Klein 4B31.8 rank points
OmniGen229.6 rank points
Ideogram 4.528.3 rank points
Vidu Q2 Image26.8 rank points
FLUX1.1 [pro] Ultra21.8 rank points
MOSS-Image-SFT21.5 rank points
Adobe Firefly Image 420.6 rank points
Sana-Sprint 1.6B 1024px20.6 rank points
FLUX.1 Kontext [pro]19 rank points
Lumina-Image 2.018.4 rank points
Boogu-Image-0.1-Turbo18.1 rank points
HiDream-O1-Image18.1 rank points
Chroma1-Flash16.2 rank points
FLUX.1 [dev]16.2 rank points
Sana-Sprint 0.6B 1024px15.9 rank points
Midjourney V8.114.3 rank points
HunyuanImage 3.012.5 rank points
AuraFlow v0.311.2 rank points
BAGEL-7B-MoT11.2 rank points
SANA-1.5 4.8B 1024px8.1 rank points
LLaDA-Image-Turbo7.8 rank points
Adobe Firefly Image 36.9 rank points
SDXL Turbo3.4 rank points
SANA-1.5 1.6B 1024px3.1 rank points

higher is betterAs of November 3, 2026Scale: 0 rank points - 100 rank points

Source: Gradually-Bildtest
gradually.ai
Methodology and context
Metric
rank-score-100
Scale
0-100
Participants
108
Sample
1
Methodology and context
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Source: Gradually-Bildtest

Gradually sample test: Product photography

The 0-100 value normalizes the mean rank from model-blind comparison rounds. One archived first output contributes per model. This remains an n = 1 sample.

MAI-Image-2.6 Flash90.3 rank points
Krea 2 Large90 rank points
Qwen Image 2.1 Turbo89.7 rank points
Qwen-Image-2.189.7 rank points
GPT Image 289.4 rank points
Seedream 5.0 Lite88.8 rank points
MAI-Image-2.688.2 rank points
BAGEL-7B-MoT87.9 rank points
Wan 2.7 Image87.9 rank points
Nano Banana 2 Lite87.2 rank points
Qwen Image 3.087.2 rank points
FLUX.2 Klein 9B86.6 rank points
GPT Image 2.5 Sunburst86.6 rank points
Wan 2.7 Image Pro86.6 rank points
MOSS-Image-SFT85.7 rank points
Bria FIBO 283.8 rank points
SenseNova U1.5 Lite83.5 rank points
Qwen Image 2.1 Pro83.2 rank points
Grok Imagine Image 1.081.3 rank points
FLUX.2 Klein 4B80.7 rank points
Krea 2 Medium Turbo80.7 rank points
Muse Image80.7 rank points
Seedream 5.0 Flash76.9 rank points
Seedream 5.0 Pro76.9 rank points
FLUX 3 Image Klein74.8 rank points
Reve 2.173.8 rank points
GPT Image 1 Mini73.5 rank points
FLUX.2 Klein 9B Preview72.6 rank points
Qwen Image 3.0 Pro71.3 rank points
Luma Uni-1.1 Max71 rank points
Recraft V4.171 rank points
MAI-Image-2.570.1 rank points
Nano Banana Pro70.1 rank points
Nano Banana 2.169.8 rank points
GPT Image 2.5 Flare69.2 rank points
Ideogram 4.568.9 rank points
Grok Imagine Image 2.067.9 rank points
FLUX.2 Flex62.6 rank points
Krea 362.6 rank points
FLUX 3 Image62 rank points
Nucleus-Image62 rank points
Kling Image 3.060.4 rank points
Luma Uni-1.159.5 rank points
FLUX.2 Max58.6 rank points
Qwen Image 2.0 Pro58.3 rank points
FLUX.2 Pro57.9 rank points
MAI-Image-2.5 Flash57.6 rank points
Wan 2.6 Text to Image53.9 rank points
GPT Image 1.552.3 rank points
HiDream-O1-Image-1.550.8 rank points
Midjourney V8.149.5 rank points
FLUX.1 [dev]46.4 rank points
FLUX.2 Dev46.4 rank points
Firefly Image Model 545.8 rank points
Nano Banana 244.9 rank points
Seedream 4.044.2 rank points
Seedream 4.544.2 rank points
Kling Image 3.0 Omni39.9 rank points
MOSS-Image-Base36.1 rank points
Recraft V4.1 Flash36.1 rank points
FLUX.1 Kontext [pro]35.8 rank points
Recraft V4.1 Utility Pro35.8 rank points
Bria FIBO Lite35.2 rank points
LLaDA-Image35.2 rank points
HunyuanImage 3.033.6 rank points
Runway Gen-4 Image32.7 rank points
Recraft V4.1 Utility32.4 rank points
Vidu Q2 Image32.4 rank points
HiDream-O1-Image31.1 rank points
MiniMax Image-0129.9 rank points
OmniGen229.9 rank points
Z-Image Turbo29.9 rank points
LongCat-Image29.3 rank points
FLUX.1 Kontext [max]28.7 rank points
FLUX1.1 [pro] Ultra28.3 rank points
LLaDA-Image-Turbo26.8 rank points
Sana-Sprint 1.6B 1024px26.8 rank points
FLUX1.1 [pro]25.5 rank points
Ideogram 4.022.1 rank points
Z-Image Base21.5 rank points
Chroma1-HD15.9 rank points
Lumina-Image 2.015.9 rank points
Chroma1-Flash15.6 rank points
Hy Image 3.5 Preview15.3 rank points
AuraFlow v0.315 rank points
Adobe Firefly Image 314.6 rank points
Adobe Firefly Image 413.7 rank points
Stable Diffusion XL 1.012.8 rank points
GLM-Image9 rank points
Boogu-Image-0.1-Base7.8 rank points
Boogu-Image-0.1-Turbo5.6 rank points
SDXL Turbo2.8 rank points
SANA-1.5 4.8B 1024px1.2 rank points
Stable Diffusion Turbo1.2 rank points
SANA-1.5 1.6B 1024px0.3 rank points

higher is betterAs of November 3, 2026Scale: 0 rank points - 100 rank points

Source: Gradually-Bildtest
gradually.ai
Methodology and context
Metric
rank-score-100
Scale
0-100
Participants
108
Sample
1
Methodology and context
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Source: Gradually-Bildtest

Gradually sample test: Character and detail

The 0-100 value normalizes the mean rank from model-blind comparison rounds. One archived first output contributes per model. This remains an n = 1 sample.

GPT Image 1.588.8 rank points
Qwen Image 2.0 Pro88.5 rank points
FLUX.2 Pro86.9 rank points
Krea 384.7 rank points
FLUX.2 Dev81.6 rank points
Kling Image 3.0 Omni81.6 rank points
Reve 2.180.1 rank points
Wan 2.6 Text to Image78.5 rank points
Wan 2.7 Image Pro78.2 rank points
Seedream 5.0 Flash75.4 rank points
FLUX.2 Flex75.1 rank points
Grok Imagine Image 2.075.1 rank points
MOSS-Image-SFT74.1 rank points
Qwen Image 3.0 Pro74.1 rank points
Seedream 4.072.9 rank points
Firefly Image Model 572.3 rank points
Z-Image Base71 rank points
Z-Image Turbo71 rank points
Bria FIBO Lite70.7 rank points
FLUX.2 Max70.4 rank points
FLUX 3 Image69.5 rank points
MAI-Image-2.5 Flash67.9 rank points
Ideogram 4.567.6 rank points
FLUX 3 Image Klein66.4 rank points
Nucleus-Image66.4 rank points
Recraft V4.1 Utility66.4 rank points
Qwen Image 2.1 Pro64.8 rank points
Recraft V4.1 Utility Pro64.8 rank points
GPT Image 2.5 Sunburst64.2 rank points
GPT Image 2.5 Flare63.2 rank points
Wan 2.7 Image63.2 rank points
MAI-Image-2.662.9 rank points
LLaDA-Image62.6 rank points
Qwen Image 3.061.7 rank points
FLUX.2 Klein 4B61.1 rank points
Muse Image61.1 rank points
Grok Imagine Image 1.060.7 rank points
Luma Uni-1.1 Max60.4 rank points
GPT Image 260.1 rank points
Seedream 5.0 Pro60.1 rank points
Kling Image 3.059.2 rank points
Ideogram 4.058.9 rank points
HiDream-O1-Image-1.558.3 rank points
Nano Banana 2.156.7 rank points
MAI-Image-2.554.8 rank points
Krea 2 Large54.2 rank points
FLUX.1 [dev]52.6 rank points
LLaDA-Image-Turbo52.6 rank points
Adobe Firefly Image 452.3 rank points
MAI-Image-2.6 Flash52 rank points
Midjourney V8.151.4 rank points
GLM-Image51.1 rank points
Chroma1-Flash50.8 rank points
FLUX.1 Kontext [pro]50.2 rank points
Hy Image 3.5 Preview49.5 rank points
Luma Uni-1.148.6 rank points
Seedream 5.0 Lite48.6 rank points
Bria FIBO 248.3 rank points
Recraft V4.148 rank points
Qwen Image 2.1 Turbo47.7 rank points
Nano Banana 2 Lite47.4 rank points
MOSS-Image-Base45.5 rank points
FLUX.2 Klein 9B Preview45.2 rank points
FLUX1.1 [pro] Ultra45.2 rank points
HiDream-O1-Image45.2 rank points
Recraft V4.1 Flash42.4 rank points
FLUX1.1 [pro]39.3 rank points
FLUX.2 Klein 9B38.9 rank points
Runway Gen-4 Image38.9 rank points
Nano Banana Pro37.1 rank points
Seedream 4.537.1 rank points
Nano Banana 236.4 rank points
SenseNova U1.5 Lite34.9 rank points
Qwen-Image-2.133.6 rank points
MiniMax Image-0132.7 rank points
BAGEL-7B-MoT32.4 rank points
GPT Image 1 Mini30.8 rank points
Krea 2 Medium Turbo29.9 rank points
FLUX.1 Kontext [max]27.1 rank points
Adobe Firefly Image 326.8 rank points
Sana-Sprint 1.6B 1024px26.2 rank points
Vidu Q2 Image26.2 rank points
HunyuanImage 3.024.3 rank points
LongCat-Image24.3 rank points
Lumina-Image 2.023.4 rank points
Chroma1-HD16.5 rank points
AuraFlow v0.316.2 rank points
OmniGen27.8 rank points
Boogu-Image-0.1-Base7.5 rank points
Stable Diffusion Turbo4.7 rank points
SDXL Turbo2.8 rank points
SANA-1.5 4.8B 1024px0.3 rank points

higher is betterAs of November 3, 2026Scale: 0 rank points - 100 rank points

Source: Gradually-Bildtest
gradually.ai
Methodology and context
Metric
rank-score-100
Scale
0-100
Participants
108
Sample
1
Methodology and context
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Source: Gradually-Bildtest

Gradually sample test: Infographic

The 0-100 value normalizes the mean rank from model-blind comparison rounds. One archived first output contributes per model. This remains an n = 1 sample.

Seedream 5.0 Pro99.1 rank points
GPT Image 2.5 Sunburst97.2 rank points
GPT Image 2.5 Flare91 rank points
Luma Uni-1.189.4 rank points
Qwen Image 2.1 Turbo88.8 rank points
Qwen Image 3.088.8 rank points
Wan 2.7 Image Pro88.5 rank points
Muse Image86.3 rank points
Seedream 5.0 Flash86 rank points
Ideogram 4.585.4 rank points
Reve 2.184.7 rank points
Qwen-Image-2.182.9 rank points
MAI-Image-2.5 Flash81.3 rank points
SenseNova U1.5 Lite80.4 rank points
Wan 2.7 Image79.4 rank points
Krea 2 Medium Turbo78.8 rank points
Luma Uni-1.1 Max78.8 rank points
Bria FIBO 278.2 rank points
FLUX 3 Image Klein77.3 rank points
Wan 2.6 Text to Image77.3 rank points
Grok Imagine Image 1.076.9 rank points
Grok Imagine Image 2.076.6 rank points
HiDream-O1-Image-1.576.3 rank points
Krea 2 Large75.7 rank points
MOSS-Image-SFT75.4 rank points
FLUX.2 Klein 9B Preview74.8 rank points
Recraft V4.1 Utility Pro74.5 rank points
Krea 373.8 rank points
Recraft V4.1 Flash73.8 rank points
MAI-Image-2.6 Flash73.5 rank points
Recraft V4.173.2 rank points
Ideogram 4.072.6 rank points
FLUX.2 Dev72 rank points
GPT Image 1.571.7 rank points
Hy Image 3.5 Preview70.7 rank points
MOSS-Image-Base70.7 rank points
MAI-Image-2.569.2 rank points
FLUX 3 Image68.5 rank points
Seedream 4.067.3 rank points
GPT Image 266.4 rank points
Nano Banana 2 Lite65.7 rank points
Nano Banana Pro64.8 rank points
Nano Banana 2.164.2 rank points
Recraft V4.1 Utility63.9 rank points
Nano Banana 263.2 rank points
Qwen Image 2.1 Pro62 rank points
Qwen Image 2.0 Pro61.7 rank points
Qwen Image 3.0 Pro61.7 rank points
MAI-Image-2.660.7 rank points
FLUX.2 Flex57 rank points
Seedream 5.0 Lite55.8 rank points
FLUX.1 Kontext [max]53.9 rank points
FLUX.2 Max53.6 rank points
FLUX.1 Kontext [pro]52.6 rank points
Kling Image 3.051.4 rank points
FLUX.2 Pro44.6 rank points
HiDream-O1-Image42.7 rank points
FLUX.2 Klein 9B41.7 rank points
FLUX.1 [dev]39.9 rank points
Z-Image Turbo37.4 rank points
Vidu Q2 Image37.1 rank points
LongCat-Image36.8 rank points
HunyuanImage 3.036.1 rank points
LLaDA-Image-Turbo35.8 rank points
Midjourney V8.135.2 rank points
LLaDA-Image32.7 rank points
Runway Gen-4 Image32.4 rank points
GPT Image 1 Mini31.8 rank points
FLUX.2 Klein 4B30.2 rank points
GLM-Image29.9 rank points
Kling Image 3.0 Omni29.6 rank points
FLUX1.1 [pro] Ultra27.7 rank points
Seedream 4.526.5 rank points
MiniMax Image-0125.5 rank points
FLUX1.1 [pro]24 rank points
Z-Image Base24 rank points
Nucleus-Image23.4 rank points
Chroma1-HD22.4 rank points
Bria FIBO Lite19.6 rank points
OmniGen219 rank points
Boogu-Image-0.1-Base15.9 rank points
Lumina-Image 2.015.9 rank points
Firefly Image Model 515 rank points
Adobe Firefly Image 412.5 rank points
Chroma1-Flash12.1 rank points
Sana-Sprint 1.6B 1024px10 rank points
Boogu-Image-0.1-Turbo8.4 rank points
SDXL Turbo8.4 rank points
SANA-1.5 1.6B 1024px7.2 rank points
AuraFlow v0.36.9 rank points
BAGEL-7B-MoT5.9 rank points
SANA-1.5 4.8B 1024px5.6 rank points
Adobe Firefly Image 35.3 rank points
Stable Diffusion Turbo4.7 rank points

higher is betterAs of November 3, 2026Scale: 0 rank points - 100 rank points

Source: Gradually-Bildtest
gradually.ai
Methodology and context
Metric
rank-score-100
Scale
0-100
Participants
108
Sample
1
Methodology and context
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Source: Gradually-Bildtest

Recorded measurement details

Gradually sample test: Typography and layout (Show measurement, test conditions, and source)
Source value
20.6
Score
20.6
Metric
rank-score-100
Unit
rank score
Direction
Higher is better
Source rank
85
Sample
1
Source type
gradually-sample-test
Evaluator
gemini-3.1-pro-preview
Retrieved at
2026-11-03
Methodology
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Mean rank
86
Individual ranks
98, 78, 82
Criterion scores
headline 1, subline 0.67, text-control 0.67, visual-brief 1, layout 0.67
Source Gradually-Bildtest
Gradually sample test: Product photography (Show measurement, test conditions, and source)
Source value
26.8
Score
26.8
Metric
rank-score-100
Unit
rank score
Direction
Higher is better
Source rank
82
Sample
1
Source type
gradually-sample-test
Evaluator
gemini-3.1-pro-preview
Retrieved at
2026-11-03
Methodology
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Mean rank
79.33
Individual ranks
79, 82, 77
Criterion scores
subject 2, time 2, watch-details 1.67, photography 2, exclusions 0.33
Source Gradually-Bildtest
Gradually sample test: Character and detail (Show measurement, test conditions, and source)
Source value
26.2
Score
26.2
Metric
rank-score-100
Unit
rank score
Direction
Higher is better
Source rank
92
Sample
1
Source type
gradually-sample-test
Evaluator
gemini-3.1-pro-preview
Retrieved at
2026-11-03
Methodology
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Mean rank
80
Individual ranks
103, 99, 38
Criterion scores
scene 1, wardrobe 1, anatomy 1, props 1, environment 1
Source Gradually-Bildtest
Gradually sample test: Infographic (Show measurement, test conditions, and source)
Source value
10
Score
10
Metric
rank-score-100
Unit
rank score
Direction
Higher is better
Source rank
97
Sample
1
Source type
gradually-sample-test
Evaluator
gemini-3.1-pro-preview
Retrieved at
2026-11-03
Methodology
One archived image per model, using the first output of the accepted test attempt. Technical repeats are disclosed for the affected image. All 108 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.
Mean rank
97.33
Individual ranks
96, 102, 94
Criterion scores
title 0.33, sequence 0.33, labels 0.33, diagram 0.33, clarity 0.33
Source Gradually-Bildtest

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 101 models

As of November 2026 · Source: gradually.ai popularity index

Over time

First value from November 5, 2026. The timeline appears from the second week.

Sana-Sprint 1.6B 1024px compared

Compare with another model

The most popular comparisons

  1. 1GPT Image 2.5 Sunburst vs. Sana-Sprint 1.6B 1024px
  2. 2GPT Image 2 vs. Sana-Sprint 1.6B 1024px
  3. 3Reve 2.1 vs. Sana-Sprint 1.6B 1024px
  4. 4Nano Banana 2 vs. Sana-Sprint 1.6B 1024px
  5. 5GPT Image 1.5 vs. Sana-Sprint 1.6B 1024px
  6. 6MAI-Image-2.5 vs. Sana-Sprint 1.6B 1024px
  7. 7Nano Banana Pro vs. Sana-Sprint 1.6B 1024px
  8. 8Nano Banana 2 Lite vs. Sana-Sprint 1.6B 1024px
  9. 9Seedream 5.0 Pro vs. Sana-Sprint 1.6B 1024px
Show all 107 comparisons
  1. 10Grok Imagine Image Quality vs. Sana-Sprint 1.6B 1024px
  2. 11FLUX.2 Max vs. Sana-Sprint 1.6B 1024px
  3. 12Qwen Image 2.0 Pro vs. Sana-Sprint 1.6B 1024px
  4. 13MAI-Image-2.5 Flash vs. Sana-Sprint 1.6B 1024px
  5. 14HiDream-O1-Image-1.5 vs. Sana-Sprint 1.6B 1024px
  6. 15Krea 2 Medium Turbo vs. Sana-Sprint 1.6B 1024px
  7. 16Seedream 4.0 vs. Sana-Sprint 1.6B 1024px
  8. 17Krea 2 Large vs. Sana-Sprint 1.6B 1024px
  9. 18Luma Uni-1.1 Max vs. Sana-Sprint 1.6B 1024px
  10. 19FLUX.2 Flex vs. Sana-Sprint 1.6B 1024px
  11. 20Recraft V4.1 Utility vs. Sana-Sprint 1.6B 1024px
  12. 21Ideogram 4.0 vs. Sana-Sprint 1.6B 1024px
  13. 22Wan 2.6 Text to Image vs. Sana-Sprint 1.6B 1024px
  14. 23FLUX.2 Pro vs. Sana-Sprint 1.6B 1024px
  15. 24HunyuanImage 3.0 Instruct vs. Sana-Sprint 1.6B 1024px
  16. 25FLUX.2 Klein 9B vs. Sana-Sprint 1.6B 1024px
  17. 26HiDream-O1-Image vs. Sana-Sprint 1.6B 1024px
  18. 27Firefly Image Model 5 vs. Sana-Sprint 1.6B 1024px
  19. 28Midjourney V8.1 vs. Sana-Sprint 1.6B 1024px
  20. 29Stable Diffusion 3.5 Large vs. Sana-Sprint 1.6B 1024px
  21. 30GPT Image 2.5 Flare vs. Sana-Sprint 1.6B 1024px
  22. 31Qwen-Image-2.1 vs. Sana-Sprint 1.6B 1024px
  23. 32MAI-Image-2.6 vs. Sana-Sprint 1.6B 1024px
  24. 33MAI-Image-2.6 Flash vs. Sana-Sprint 1.6B 1024px
  25. 34Muse Image vs. Sana-Sprint 1.6B 1024px
  26. 35Grok Imagine Image 2.0 vs. Sana-Sprint 1.6B 1024px
  27. 36FLUX 3 Image vs. Sana-Sprint 1.6B 1024px
  28. 37FLUX 3 Image Klein vs. Sana-Sprint 1.6B 1024px
  29. 38Nano Banana 2.1 vs. Sana-Sprint 1.6B 1024px
  30. 39Ideogram 4.5 vs. Sana-Sprint 1.6B 1024px
  31. 40Hy Image 3.5 Preview vs. Sana-Sprint 1.6B 1024px
  32. 41Recraft V4.1 vs. Sana-Sprint 1.6B 1024px
  33. 42Recraft V4.1 Flash vs. Sana-Sprint 1.6B 1024px
  34. 43Bria FIBO 2 vs. Sana-Sprint 1.6B 1024px
  35. 44Krea 3 vs. Sana-Sprint 1.6B 1024px
  36. 45Qwen Image 3.0 Pro vs. Sana-Sprint 1.6B 1024px
  37. 46Qwen Image 3.0 vs. Sana-Sprint 1.6B 1024px
  38. 47Qwen Image 2.1 Pro vs. Sana-Sprint 1.6B 1024px
  39. 48Qwen Image 2.1 Turbo vs. Sana-Sprint 1.6B 1024px
  40. 49Wan 2.7 Image Pro vs. Sana-Sprint 1.6B 1024px
  41. 50Wan 2.7 Image vs. Sana-Sprint 1.6B 1024px
  42. 51Seedream 5.0 Flash vs. Sana-Sprint 1.6B 1024px
  43. 52SenseNova U1.5 Lite vs. Sana-Sprint 1.6B 1024px
  44. 53Kling Image 3.0 vs. Sana-Sprint 1.6B 1024px
  45. 54Kling Image 3.0 Omni vs. Sana-Sprint 1.6B 1024px
  46. 55Vidu Q2 Image vs. Sana-Sprint 1.6B 1024px
  47. 56GLM-Image vs. Sana-Sprint 1.6B 1024px
  48. 57MiniMax Image-01 vs. Sana-Sprint 1.6B 1024px
  49. 58Z-Image Turbo vs. Sana-Sprint 1.6B 1024px
  50. 59Luma Uni-1.1 vs. Sana-Sprint 1.6B 1024px
  51. 60Runway Gen-4 Image vs. Sana-Sprint 1.6B 1024px
  52. 61Adobe Firefly Image 3 vs. Sana-Sprint 1.6B 1024px
  53. 62Adobe Firefly Image 4 vs. Sana-Sprint 1.6B 1024px
  54. 63Adobe Firefly Image 4 Ultra vs. Sana-Sprint 1.6B 1024px
  55. 64Stable Diffusion 3.5 Medium vs. Sana-Sprint 1.6B 1024px
  56. 65Stable Diffusion 3.5 Large Turbo vs. Sana-Sprint 1.6B 1024px
  57. 66Bria FIBO Lite vs. Sana-Sprint 1.6B 1024px
  58. 67Recraft V4.1 Utility Pro vs. Sana-Sprint 1.6B 1024px
  59. 68Seedream 4.5 vs. Sana-Sprint 1.6B 1024px
  60. 69Seedream 5.0 Lite vs. Sana-Sprint 1.6B 1024px
  61. 70FLUX.2 Klein 9B Preview vs. Sana-Sprint 1.6B 1024px
  62. 71GPT Image 1 Mini vs. Sana-Sprint 1.6B 1024px
  63. 72ChatGPT Image Latest (API-Alias) vs. Sana-Sprint 1.6B 1024px
  64. 73Nano Banana (Gemini 2.5 Flash Image) vs. Sana-Sprint 1.6B 1024px
  65. 74FLUX.2 Klein 4B vs. Sana-Sprint 1.6B 1024px
  66. 75FLUX.2 Dev vs. Sana-Sprint 1.6B 1024px
  67. 76FLUX1.1 [pro] vs. Sana-Sprint 1.6B 1024px
  68. 77FLUX1.1 [pro] Ultra vs. Sana-Sprint 1.6B 1024px
  69. 78FLUX.1 [dev] vs. Sana-Sprint 1.6B 1024px
  70. 79FLUX.1 Kontext [pro] vs. Sana-Sprint 1.6B 1024px
  71. 80FLUX.1 Kontext [max] vs. Sana-Sprint 1.6B 1024px
  72. 81Stable Diffusion XL 1.0 vs. Sana-Sprint 1.6B 1024px
  73. 82Stable Diffusion 3 Medium vs. Sana-Sprint 1.6B 1024px
  74. 83SDXL Turbo vs. Sana-Sprint 1.6B 1024px
  75. 84Stable Diffusion Turbo vs. Sana-Sprint 1.6B 1024px
  76. 85Grok Imagine Image 1.0 vs. Sana-Sprint 1.6B 1024px
  77. 86MOSS-Image-Base vs. Sana-Sprint 1.6B 1024px
  78. 87MOSS-Image-SFT vs. Sana-Sprint 1.6B 1024px
  79. 88LLaDA-Image vs. Sana-Sprint 1.6B 1024px
  80. 89LLaDA-Image-Turbo vs. Sana-Sprint 1.6B 1024px
  81. 90Nucleus-Image vs. Sana-Sprint 1.6B 1024px
  82. 91LongCat-Image vs. Sana-Sprint 1.6B 1024px
  83. 92BAGEL-7B-MoT vs. Sana-Sprint 1.6B 1024px
  84. 93OmniGen2 vs. Sana-Sprint 1.6B 1024px
  85. 94Kandinsky-5.0-T2I-Lite-SFT vs. Sana-Sprint 1.6B 1024px
  86. 95Kandinsky-5.0-T2I-Lite-Pretrain vs. Sana-Sprint 1.6B 1024px
  87. 96Boogu-Image-0.1-Base vs. Sana-Sprint 1.6B 1024px
  88. 97Boogu-Image-0.1-Turbo vs. Sana-Sprint 1.6B 1024px
  89. 98SANA-1.5 1.6B 1024px vs. Sana-Sprint 1.6B 1024px
  90. 99SANA-1.5 4.8B 1024px vs. Sana-Sprint 1.6B 1024px
  91. 100Sana-Sprint 0.6B 1024px vs. Sana-Sprint 1.6B 1024px
  92. 101Sana-Sprint 1.6B 1024px vs. Chroma1-HD
  93. 102Sana-Sprint 1.6B 1024px vs. Chroma1-Flash
  94. 103Sana-Sprint 1.6B 1024px vs. AuraFlow v0.3
  95. 104Sana-Sprint 1.6B 1024px vs. PixArt-Sigma-XL-2-1024-MS
  96. 105Sana-Sprint 1.6B 1024px vs. Lumina-Image 2.0
  97. 106Sana-Sprint 1.6B 1024px vs. HunyuanImage 3.0
  98. 107Sana-Sprint 1.6B 1024px vs. Z-Image Base

All specifications

Architecture

Parameters
1.6B
Source: Parameters

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Weights
Open weights
Source: Weights
Access
Local
Source: Access

Further details

Checkpoint
Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers
Source: Checkpoint
Checkpoint lineage
Separate distilled speed checkpoint in the SANA-Sprint line; the official example uses two steps, while the model card describes adaptive execution with one to four steps.
Source: Checkpoint lineage
Release
NVlabs dates the release of SANA-Sprint code and weights to March 22, 2025.
Source: Release
License and text encoder
Apache-2.0; the model card also applies Google's Gemma 2 2B IT Terms of Use and Gemma Prohibited Use Policy.
Source: License and text encoder
Intended use
The model card describes the intended use as research.
Source: Intended use

Frequently asked questions about Sana-Sprint 1.6B 1024px

How good is Sana-Sprint 1.6B 1024px?

Rank 96 of 108 in our own test.

GraduallyBench from Nov 3, 2026

GraduallyBenchour own rating, 0 to 100 · higher is better
Adobe Firefly Image 4 Ultra23
Chroma1-HD23
OmniGen222
Sana-Sprint 1.6B 1024pxRank 96 of 10821
Lumina-Image 2.018
Adobe Firefly Image 313
PixArt-Sigma-XL-2-1024-MS13

What is Sana-Sprint 1.6B 1024px good at?

Best at Product photography (27 out of 100), weakest at Infographic (10).

GraduallyBench, one image per task

  1. Sana-Sprint 1.6B 1024px: Typography and layoutTypography and layoutLegible text, hierarchy, and composition21out of 100Rank 85 of 108 in this task
  2. Sana-Sprint 1.6B 1024px: Product photographyProduct photographyMaterials, reflections, and fine details27out of 100Rank 82 of 108 in this task
  3. Sana-Sprint 1.6B 1024px: Character and detailCharacter and detailAnatomy, clothing, and spatial consistency26out of 100Rank 92 of 108 in this task
  4. Sana-Sprint 1.6B 1024px: InfographicInfographicNumbers, labels, and visual organization10out of 100Rank 97 of 108 in this task

Sources and data date

Show all 9 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.