Skip to main content

Firefly Image Model 5vs.SDXL Turbo

Which one is better?

In our own test, Firefly Image Model 5 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.

Firefly Image Model 5: Typography and layout, first image from the fixed test run
Firefly Image Model 586 out of 100
SDXL Turbo: Typography and layout, first image from the fixed test run
SDXL Turbo3 out of 100

Result for “Typography and layout”:Firefly Image Model 5 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

Firefly Image Model 5: manual, one request, first output, Firefly Image 5, 1:1, 1K, no reference image, no negative prompt, 10 Adobe credits, generated Aug 16, 2026, 12:14 PM. Source

SDXL Turbo: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/sdxl-turbo@71153311d3dbb46851df1931d3ca6e939de83304; native 1024x1024, 1:1; one request, first output; steps=1, guidance=0.0, seed=660064698563452219; mps for text encoder and denoising; cpu for native VAE decode; float16 for text encoder and transformer; float32 for VAE; native tokenizer truncation: tokenizer 80 to 77 tokens, tokenizer_2 80 to 77 tokens; archived input unchanged, generated Nov 2, 2026, 6:23 PM. Source

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

Firefly Image Model 5 image SHA 256: 6a8e97db33824727599cf62339ff714cfb836a96a5f078010bb7760d7372f3d4

SDXL Turbo image SHA 256: 9ee6443f4690649e93bdca408e5e8d317b312244636a3af47a02fe14eaf6c20c

Infographic

Firefly Image Model 5: manual, one request, first output, Firefly Image 5, 1:1, 1K, no reference image, no negative prompt, 10 Adobe credits, generated Aug 16, 2026, 12:14 PM. Source

SDXL Turbo: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/sdxl-turbo@71153311d3dbb46851df1931d3ca6e939de83304; native 1024x1024, 1:1; one request, first output; steps=1, guidance=0.0, seed=6060807684445796734; mps for text encoder and denoising; cpu for native VAE decode; float16 for text encoder and transformer; float32 for VAE, generated Nov 2, 2026, 6:23 PM. Source

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

Firefly Image Model 5 image SHA 256: 8fa6d9b40c417847061ec33d789ad5bf91f1e85da586515c6226ce6db825d1ba

SDXL Turbo image SHA 256: 20395d858252aa131f235baa1f514039503a52dfec958c8f5b299db708bf4090

Product photography

Firefly Image Model 5: manual, one request, first output, Firefly Image 5, 1:1, 1K, no reference image, no negative prompt, 10 Adobe credits, generated Aug 16, 2026, 12:14 PM. Source

SDXL Turbo: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/sdxl-turbo@71153311d3dbb46851df1931d3ca6e939de83304; native 1024x1024, 1:1; one request, first output; steps=1, guidance=0.0, seed=4654331835179858246; mps for text encoder and denoising; cpu for native VAE decode; float16 for text encoder and transformer; float32 for VAE; native tokenizer truncation: tokenizer 80 to 77 tokens, tokenizer_2 80 to 77 tokens; archived input unchanged, generated Nov 2, 2026, 6:22 PM. Source

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

Firefly Image Model 5 image SHA 256: c36dab49ebe40473fa9e9a61b2b02fe36c4cd3536cbb6aac1d0ad0f8944d8bfc

SDXL Turbo image SHA 256: 75e5b85283110815e51a0470c937c3e42407244b50d918a3c0c54e10998a4b4c

Typography and layout

Firefly Image Model 5: manual, one request, first output, Firefly Image 5, 1:1, 1K, no reference image, no negative prompt, 10 Adobe credits, generated Aug 16, 2026, 12:14 PM. Source

SDXL Turbo: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/sdxl-turbo@71153311d3dbb46851df1931d3ca6e939de83304; native 1024x1024, 1:1; one request, first output; steps=1, guidance=0.0, seed=1511362670078321145; mps for text encoder and denoising; cpu for native VAE decode; float16 for text encoder and transformer; float32 for VAE, generated Nov 2, 2026, 6:21 PM. Source

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

Firefly Image Model 5 image SHA 256: cf8a921a221de5e456df2311482fc999303f5438270fb1a77c1be2dd3d9afc0b

SDXL Turbo image SHA 256: 963088c72f75c98a95fd71be5f8d6e14fdf17061ae984f1109522a39be24ac76

The numbers at a glance

GraduallyBenchour own rating, 0 to 100 · higher is better
55

Firefly Image Model 5

Rank 58 of 108

4

SDXL Turbo

Rank 105 of 108

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.

Firefly Image Model 5

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known (access: API, Web app).
Weights
Closed weights.

SDXL Turbo

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 from Nov 3, 2026 · Subscription database from Sep 29, 2026 (39 days old)

All data side by side

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

KennzahlFirefly Image Model 5SDXL Turbo
Ratings
Arena ratingfrom votes by users, higher is bettern/an/a
Arena rankn/an/a
Arena votesmore votes, a safer ratingn/an/a
GraduallyBenchour own rating, 0 to 100554
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition863
Product photographyMaterials, reflections, and fine details463
Character and detailAnatomy, clothing, and spatial consistency723
InfographicNumbers, labels, and visual organization158
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
ReleasedOct 28, 2025n/a
Weightsopen means: runs locallyproprietaryopen
LifecycleGenerally available since March 19, 2026Older open fast checkpoint; no active hosted API ID claimed in the reviewed model list
AccessAPI, Web applocal
Parametersnot publishednot published
Largest output4 Megapixelnot 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: Firefly Image Model 5 model source, status source (verified Aug 15, 2026) · SDXL Turbo model source, status 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 Firefly Image Model 5 and SDXL Turbo from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare Firefly Image Model 5 and SDXL Turbo with the models people compare them with most often.

Compare another matchup