- Home
- Image model comparison
- Adobe Firefly Image 3 vs. Kandinsky-5.0-T2I-Lite-SFT
AdobeKandinsky LabImage model matchup
Adobe Firefly Image 3vs.Kandinsky-5.0-T2I-Lite-SFT
Which one is better?
In our own benchmark GraduallyBench, Kandinsky-5.0-T2I-Lite-SFT leads. Neither is in the arena. Neither has an API price.
Adobe Firefly Image 3
Rank 103 of 108
Kandinsky-5.0-T2I-Lite-SFT
Rank 82 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.
Test images from GraduallyBench
Same task, the first image of each. The task with the biggest difference is preselected.


Result for “Infographic”:Kandinsky-5.0-T2I-Lite-SFT ahead
What the rating looks at: Numbers, labels, and visual organization.
“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 3: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Firefly Image 3, provider-default random seed, native resolution provider default, fast mode False, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square cinematic full-body portrait of a fictional bicycle courier waiting u 715099.jpg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:28 PM. Source
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=89463658088346984; 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, 8:12 PM. Source
Protocol gradually-image-comparison-v1. Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6
Adobe Firefly Image 3 image SHA 256: 9d5906a1ead81d8ccac7833e355e8ca2eb9b501c1ad6eb8afe086eb8aeb72f42
Kandinsky-5.0-T2I-Lite-SFT image SHA 256: 8d193e702ad1aa0fccdb45f5d1474d60e21d455fa58d13470edd2796af0f2aed
Infographic
Adobe Firefly Image 3: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Firefly Image 3, provider-default random seed, native resolution provider default, fast mode False, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square German infographic titled SO FUNKTIONIERT PHOTOSYNTHESE. Show exactly 715099.jpg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:28 PM. Source
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=649868597087646690; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE, generated Nov 2, 2026, 8:21 PM. Source
Protocol gradually-image-comparison-v1. Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f
Adobe Firefly Image 3 image SHA 256: 9be22655b492fe44a2b5f906d12a9d80d68967e771177c3a7e7e9d9b8d492ad0
Kandinsky-5.0-T2I-Lite-SFT image SHA 256: e102016732db9e8e463504a83ac0770ff8a3c4c77918143d0f9dae8498c79101
Product photography
Adobe Firefly Image 3: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Firefly Image 3, provider-default random seed, native resolution provider default, fast mode False, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square premium product photograph of a brushed titanium wristwatch standing 715099.jpg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:28 PM. Source
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
Protocol gradually-image-comparison-v1. Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3
Adobe Firefly Image 3 image SHA 256: 5fc5c7d52a0a0eab5d6e0c078dfcd1723ddfdce1f4f28ee08a68bde942e89fab
Kandinsky-5.0-T2I-Lite-SFT image SHA 256: 73b31dc5a48059f7712c6a125ac4855f2401133101172c4bfbaa11b76c5ceee1
Typography and layout
Adobe Firefly Image 3: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Firefly Image 3, provider-default random seed, native resolution provider default, fast mode False, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square editorial poster for an imaginary night train called MONDFALTER. Show 715099.jpg, source 2048x2048, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:28 PM. Source
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
Protocol gradually-image-comparison-v1. Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419
Adobe Firefly Image 3 image SHA 256: aa88c80c984b7671eef720bb790dfde56ab82609939bf1412db2fc998ef592e7
Kandinsky-5.0-T2I-Lite-SFT image SHA 256: a84280dd219692f7b20722a37491d6788d1ecdc594f816fa1203981642501ab2
Subscription and API
Adobe Firefly Image 3
- Subscription
- n/a No plan in Germany names exactly this model.
- Via API
- No API price known (access: Web app).
- Weights
- Unknown.
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).
- Weights
- Open weights.
Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.
GraduallyBench from Nov 7, 2026 · Subscription database from Sep 29, 2026 (42 days old)
All data side by side
The better value is bold. For ratings only when the gap is clear.
| Kennzahl | Adobe Firefly Image 3 | Kandinsky-5.0-T2I-Lite-SFT |
|---|---|---|
| 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 benchmark, 0 to 100 | 11 | 27 |
| GraduallyBench by task | ||
| Typography and layoutLegible text, hierarchy, and composition | 5 | 18 |
| Product photographyMaterials, reflections, and fine details | 16 | 28 |
| Character and detailAnatomy, clothing, and spatial consistency | 18 | 37 |
| InfographicNumbers, labels, and visual organization | 5 | 27 |
| API price | ||
| Per imagelower is better | n/a | n/a |
| 100 images | n/a | n/a |
| Profile | ||
| Released | Apr 23, 2024 | n/a |
| Weightsopen means: runs locally | unknown | open |
| Access | Web app | local |
| Parameters | not published | 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: Adobe Firefly Image 3 model source (verified Nov 1, 2026) · Kandinsky-5.0-T2I-Lite-SFT model 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 3 and Kandinsky-5.0-T2I-Lite-SFT from the same arena and category. Older model versions are not used as substitutes.