OutfitGen

AI Image Editing Leaderboard

13 image-editing models, the same 18 photo edits, 5 runs each, judged with the model names hidden. Maintained by the OutfitGen Team and re-run as new models ship.

Snapshot
2026-10 · v1.3
Updated
October 19, 2026
Runs
1,170
Source
Lab data

Edits done right

Higher is better

Flux 2 Flash, Flux 2 Turbo, Seedream 5 Flash and Seedream 5 Pro got 17 of 18 edits right, the most of any model.
Flux 2 Flash17/18
Flux 2 Turbo17/18
Seedream 5 Flash17/18
Seedream 5 Pro17/18
Flux 216/18
Seedream 5 Lite16/18
Qwen Image 315/18
Nano Banana 215/18
Grok Imagine 2.014/18
GPT Image 2.5 Flare (medium)14/18
GPT Image 2.5 Flare (high)14/18
Nano Banana 2.113/18
Muse Image12/18

Refusal rate

Lower is better

7 of 13 models refused none of their ordinary requests; Muse Image refused 26%.
Flux 2 Flash0%
Flux 2 Turbo0%
Seedream 5 Flash0%
Seedream 5 Pro0%
Flux 20%
Seedream 5 Lite0%
Qwen Image 30%
Nano Banana 2.115%
Grok Imagine 2.017%
Nano Banana 221%
GPT Image 2.5 Flare (medium)22%
GPT Image 2.5 Flare (high)24%
Muse Image26%

Median time per edit

Lower is better

Flux 2 Flash was fastest at 4.0 s per edit, 8x quicker than Seedream 5 Lite.
Flux 2 Flash4.0 s
Flux 2 Turbo5.8 s
Nano Banana 211.3 s
Nano Banana 2.111.5 s
Flux 211.9 s
Grok Imagine 2.013.2 s
Qwen Image 314.5 s
GPT Image 2.5 Flare (medium)15.1 s
Seedream 5 Flash15.2 s
Muse Image16.5 s
GPT Image 2.5 Flare (high)21.6 s
Seedream 5 Pro27.2 s
Seedream 5 Lite32.4 s

Everyday fashion edits

AI image editing leaderboard. Select a column heading to sort.
Model
1Flux 2 FlashBlack Forest Labs · Dec 202517 / 18✓ 0%0 of 90 runs4.0 s
2Flux 2 TurboBlack Forest Labs · Dec 202517 / 18✓ 0%0 of 90 runs5.8 s
3Seedream 5 FlashByteDance · Sep 202617 / 18✓ 0%0 of 90 runs15.2 s
4Seedream 5 ProByteDance · Jul 202617 / 18✓ 0%0 of 90 runs27.2 s
5Flux 2Black Forest Labs · Nov 202516 / 18✓ 0%0 of 90 runs11.9 s
6Seedream 5 LiteByteDance · Feb 202616 / 18✓ 0%0 of 90 runs32.4 s
7Qwen Image 3Alibaba · Jul 202615 / 18✓ 0%0 of 89 runs14.5 s
8Nano Banana 2Google · Feb 202615 / 1821%19 of 90 runs11.3 s
9Grok Imagine 2.0xAI · Aug 202614 / 1817%15 of 89 runs13.2 s
10GPT Image 2.5 Flare (medium)OpenAI · Sep 202614 / 1822%20 of 90 runs15.1 s
11GPT Image 2.5 Flare (high)OpenAI · Sep 202614 / 1824%22 of 90 runs21.6 s
12Nano Banana 2.1Google · Oct 202613 / 1815%13 of 87 runs11.5 s
13Muse ImageMeta · Sep 202612 / 1826%23 of 89 runs16.5 s
Multi-modelOutfitGen EngineRoutes each edit across top models · tested October 202616 / 18✓ 0%Delivered 90 of 90 runs16.7 s

Ranked by edits done right, then refusal rate, then median time. OutfitGen Engine combines several models, so it is shown alongside the ranking. One edit is about 6 points on an 18-edit test, so treat a one-edit gap as close. Per-case results are in the source study.

Virtual try-on

13 models copy a garment from a product photo onto a person: 13 cases, 3 runs each, judged blind. Read the study.

Virtual try-on panel, in the study's rank order.
RankModelTry-ons done rightof 13, higher is betterGarment copied rightof 13Same person keptof 13
1Nano Banana 2.113 / 131313
2Seedream 5 Flash13 / 131313
3GPT Image 2.5 Flare (high)13 / 131313
4GPT Image 2.5 Flare (medium)12 / 131213
5Muse Image12 / 131213
6Nano Banana 211 / 131213
7Seedream 5 Pro11 / 131213
8Flux 26 / 13810
9Qwen Image 36 / 13612
10Flux 2 Flash5 / 13611
11Flux 2 Turbo4 / 13610
12FASHN Try-On v1.64 / 13513
13Grok Imagine 2.00 / 13013
Multi-modelOutfitGen EngineRoutes each edit across top models · tested October 202613 / 131313

Ranked by try-ons done right (garment, person and pose right in every run), then median time in the study session. FASHN Try-On v1.6 is a dedicated try-on model; the others are general image editors. Seedream 5 Lite was not in this study. OutfitGen Engine combines several models, so it is shown alongside the ranking.

Portrait and scene edits

4 models, 11 edits, 3 runs each. Read the study.

ModelFace kepthigher is betterUnasked-for changesfewer is betterOutfit copied from a photocomplete runs
GPT Image 2.5 Flare (medium)9 of 9 runs0 of 112 of 3 runs
GPT Image 2.5 Flare (high)9 of 9 runs2 of 112 of 3 runs
Nano Banana 29 of 9 runs4 of 113 of 3 runs
Seedream 5 Pro9 of 9 runsScene kept, not relit3 of 3 runs

Method

Test set
18 everyday fashion edits on synthetic adult photos: outfit changes, new backdrops, swimwear, activewear and catalog lingerie.
Runs
Every model got the same photo and instruction 5 times, through each model's hosted API, with no tuned prompts.
Edits done right
Edits a reviewer rated correct in every delivered run, judging shuffled contact sheets before the model names were revealed. An edit refused every time counts as not done.
Refusal rate
Runs the model declined with a content-policy refusal, out of runs that returned an answer. Every request was ordinary, so every refusal is a false positive.
Median time
Median seconds from request to delivered image, measured in the same session for every model. Provider queues move absolute times; the order is the finding.
Lab data only
Every number comes from test photos made for these studies. No production traffic and no user photos are used.

How to cite

OutfitGen. (2026). AI Image Editing Leaderboard, snapshot 2026-10, version 1.3. OutfitGen Research. https://outfitgen.ai/research/leaderboard

@misc{outfitgen-leaderboard-2026-10,
  title  = {AI Image Editing Leaderboard},
  author = {{OutfitGen}},
  year   = {2026},
  note   = {OutfitGen Research, snapshot 2026-10, version 1.3},
  url    = {https://outfitgen.ai/research/leaderboard}
}

Free to reuse with attribution under CC BY 4.0.

Snapshots

  1. 2026-10 · v1.3 · October 19, 2026

    Added the virtual try-on panel: 13 models, including the dedicated try-on model FASHN Try-On v1.6, copying 5 garments from product photos onto 9 photos of people, 13 cases, three runs each, judged blind. Nano Banana 2.1, Seedream 5 Flash and GPT Image 2.5 Flare (high) got all 13 right, as did OutfitGen Engine, shown alongside the ranking. The main table did not change.

    Which AI model copies a garment from a product photo best?

  2. 2026-10 · v1.2 · October 19, 2026

    Added OutfitGen Engine alongside the ranking: OutfitGen's multi-model system, which routes each edit across models, run on the same 18 edits five times each. It delivered all 90 requests, refused none and got 16 of 18 edits right under blind judging. Its median time is scaled to the September session through a same-day Nano Banana 2 control. No ranked row changed.

  3. 2026-10 · v1.1 · October 14, 2026

    Added Nano Banana 2.1 (Google, released 6 October 2026) on the same 18 edits, five runs each, judged blind: 13 of 18 edits done right, 13 of 87 ordinary requests refused. Its median time is scaled to the September session through a same-day Nano Banana 2 control (41.8 s against the control's 41.0 s in October; 11.3 s for the control in September). No other row changed.

    What Nano Banana 2.1's results mean if you edit photos

  4. 2026-09 · v1.0 · September 30, 2026

    First snapshot: 12 models on the 18-edit everyday fashion set, plus the 4-model portrait and scene panel.

Want a model added? Write to the address on the about page.

OutfitGen is an AI photo editor for outfits, backgrounds and poses. These tests decide which models OutfitGen Engine trusts for which edits.

Try OutfitGen