whatmodel.sh / image / Krea 2 Large
Krea 2 Large
↗ share
+ contribute
Krea 2 Large is a closed-weights image model from Krea, released May 2026. Licence: proprietary.
Catalogue identity notes
Comparison-only. Arena text_to_image entry 'krea-2-large' (krea, Proprietary), first listed 2026-06-05. Separate model size from Krea 2 Medium/Turbo.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Krea 2 Large, out of 197 with a score, then more from Krea.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 56 | Krea 2 Turbo | 59±3 | api $0.015/image +local | ||
| 57 |  GPT Image 1 Mini | 59±2 | api $0.011/image | ||
| 58 | Krea 2 Large | 59±3 | api $0.060/image | ||
| 59 |  Qwen-Image-Edit-2509 | 59±3 | api $0.030/image +local | ||
| 60 |  HiDream-O1-Image | 58±2 | api $0.010/image +local | ||
| more from Krea | |||||
| 51 | Krea 2 Medium | 60±3 | api $0.030/image | ||
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▂▁▁ #48 of 126 * · 97% of its score · 1 test
Beats Wan 2.7 Image here, though they rank higher overall. Trails Z-Image (Base), FLUX.2 [dev] here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1111.5 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 28/75 | 97% |
$ where to run it
Through an API
api · $0.060/image · www.krea.ai ↗ · price sourceUSD per generated image, Krea 2 Large text-to-image on the Krea API: fixed per-generation price $0.060 (with style references $0.065, with moodboards $0.070). Product: Krea API. API model: krea-2/large (POST /generate/image/krea/krea-2/large). Settings: resolution=1K (the only resolution offered), no style references or moodboards, one image. Price basis: published fixed list price. Paid from a prepaid USD API balance. Currency: USD. Krea official API documentation, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 97%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 1 | 97% |
| prior · pull toward the middle | 3% | |
| weighted average | = 58.6 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json