Skip to main content

AdobeStability AIImage model matchup

Adobe Firefly Image 4vs.Stable Diffusion XL 1.0

Which one is better?

In our own benchmark GraduallyBench Image v2, Adobe Firefly Image 4 leads. Neither is in the arena. Neither has an API price.

GraduallyBench Image v2Our own benchmark0 to 100 · higher is better
30

Adobe Firefly Image 4

Rank 80 of 108

6

Stable Diffusion XL 1.0

Rank 106 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.

Adobe Firefly Image 4: Character and detail, first image from the fixed test run
Adobe Firefly Image 462 out of 100
Stable Diffusion XL 1.0: Character and detail, first image from the fixed test run
Stable Diffusion XL 1.09 out of 100

Result for “Character and detail”:Adobe Firefly Image 4 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”: 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

Adobe Firefly Image 4: manual, 1:1, one request, first output, one output observed, exact UI model Firefly Image 4, provider-default random seed, native 2K square output, no reference images, no selected effects, default content settings, source UI file Create a square cinematic full-b 60374 ydr.ffgenimg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 9:42 PM. Source

Stable Diffusion XL 1.0: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/stable-diffusion-xl-base-1.0@462165984030d82259a11f4367a4eed129e94a7b; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0, seed=268378870826470633; 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, 6:07 PM. Source

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

Adobe Firefly Image 4 image SHA 256: a0305ed203aa5f66fa5082f78a169737d0cea9fc6d7bdac14eb6c874521a6669

Stable Diffusion XL 1.0 image SHA 256: 26d3c3d3e687614e24dd12191246bc1d96c1576d31f9211840a3e02b64d4d507

Infographic

Adobe Firefly Image 4: manual, 1:1, one request, first output, one output observed, exact UI model Firefly Image 4, provider-default random seed, native 2K square output, no reference images, no selected effects, default content settings, source UI file Create a square German infograph 211113 2kW.ffgenimg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 9:42 PM. Source

Stable Diffusion XL 1.0: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/stable-diffusion-xl-base-1.0@462165984030d82259a11f4367a4eed129e94a7b; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0, seed=5455008934753613262; mps for text encoder and denoising; cpu for native VAE decode; float16 for text encoder and transformer; float32 for VAE, generated Nov 2, 2026, 6:08 PM. Source

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

Adobe Firefly Image 4 image SHA 256: 6a23e56ba8c63ec5461c8a20fabc74aff347088ad49b3cc7aa39eb8088d33c23

Stable Diffusion XL 1.0 image SHA 256: ebfe8d1c223478c94ff1973ab2600cd4f696b40b8c3388ca40f26f52c83afdb2

Product photography

Adobe Firefly Image 4: manual, 1:1, one request, first output, one output observed, exact UI model Firefly Image 4, provider-default random seed, native 2K square output, no reference images, no selected effects, default content settings, source UI file Create a square premium product 776320 41X.ffgenimg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 9:42 PM. Source

Stable Diffusion XL 1.0: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/stable-diffusion-xl-base-1.0@462165984030d82259a11f4367a4eed129e94a7b; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0, seed=490593220006868735; 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, 6:06 PM. Source

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

Adobe Firefly Image 4 image SHA 256: 4f93f6c8da78501a95fccc17a8464c95f590799028c4a62ed87d15342e123182

Stable Diffusion XL 1.0 image SHA 256: f59af9c84f6fbb3e4ca34bf87ebb0f7c088e8caa520fa4cdf815a96d1bffda83

Typography and layout

Adobe Firefly Image 4: manual, 1:1, one request, first output, one output observed, exact UI model Firefly Image 4, provider-default random seed, native 2K square output, no reference images, no selected effects, default content settings, source UI file Create a square editorial poster 565284 h6v.ffgenimg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 9:42 PM. Source

Stable Diffusion XL 1.0: manual, local PyTorch 2.13.0, Diffusers 0.36.0; stabilityai/stable-diffusion-xl-base-1.0@462165984030d82259a11f4367a4eed129e94a7b; native 1024x1024, 1:1; one request, first output; steps=50, guidance=5.0, seed=253938565953989943; mps for text encoder and denoising; cpu for native VAE decode; float16 for text encoder and transformer; float32 for VAE, generated Nov 2, 2026, 6:05 PM. Source

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

Adobe Firefly Image 4 image SHA 256: 97ad71052994f6f16c416e03bb57c37b9e3a7c7be41377ee5f01ebd1fb253de2

Stable Diffusion XL 1.0 image SHA 256: c81e5d0d70afcb53fcffb51a0d548041fd0b33df300aed14b8ecd354aaaaec4e

Subscription and API

Adobe Firefly Image 4

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

Stable Diffusion XL 1.0

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known (access: API, 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 (48 days old)

All data side by side

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

KennzahlAdobe Firefly Image 4Stable Diffusion XL 1.0
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 100306
GraduallyBench Image v2 by task
Typography and layoutLegible text, hierarchy, and composition213
Product photographyMaterials, reflections, and fine details234
Character and detailAnatomy, clothing, and spatial consistency629
InfographicNumbers, labels, and visual organization167
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
ReleasedApr 24, 2025n/a
Weightsopen means: runs locallyunknownopen
Lifecycleno noticeOlder open checkpoint; provider still lists it in its legacy model overview
AccessWeb appAPI, local
Parametersnot publishednot published
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: Adobe Firefly Image 4 model source (verified Nov 1, 2026) · Stable Diffusion XL 1.0 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 Adobe Firefly Image 4 and Stable Diffusion XL 1.0 from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare Adobe Firefly Image 4 and Stable Diffusion XL 1.0 with the models people compare them with most often.

Compare another matchup