whatmodel.sh / image / P-Image-Edit

P-Image-Edit

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

P-Image-Edit is a closed-weights image model from Pruna, released December 2025. Licence: proprietary.

Catalogue identity notes

Arena entry 'p-image-edit' (image edit). Released 2025-12: Pruna 2025 recap: 'In December 2025, we launched P-Image and P-Image Edit'. Pruna's hosted image-editing model (official Replicate model prunaai/p-image-edit); a separate model from P-Image.

55.9±4.0#62 of 144 image modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of P-Image-Edit, out of 197 with a score, then more from Pruna.

#modelscorewhereRAMreleased
72LongCat-Image-Edit Meituan56±2api $0.15/image +local~36GB2025-12
73Seedream 3.0 ByteDance Seed56±2comparison only2025-04
74P-Image-Edit Pruna56±4api $0.010/image2025-12
75FireRed-Image-Edit-1.0 FireRedTeam (Xiaohongshu)56±4comparison only2026-02
76Qwen-Image-2512 Alibaba56±1api $0.020/image +local~22GB2025-12
more from Pruna
98P-Image Pruna51±2api $0.0050/image2025-12

see all image models · find the ones that fit your machine

$ what it's good at

image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #41 of 62 * · 93% of its score · 1 test

Beats GPT Image 1 Mini here, though they rank higher overall. Trails FLUX.2 [klein] 9B, Qwen-Image-Edit here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image edit1210.7 ✎▂▁▁▂▆▇█▄▆▅▁▂ beats 13/53avg 1153▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%typical

$ where to run it

Through an API

api · Replicate · $0.010/image · replicate.com ↗ · price sourceUSD per output image on Replicate: the model's billing config lists '$0.01 per output image' ('or 100 images for $1'). Product: Replicate model API (Pruna's official model). API model: prunaai/p-image-edit. Settings: one output image. Price basis: per-output tariff (not hardware time). Currency: USD. Replicate model page, observed 2026-10-07.

$ how the score was worked out · LMArena leaderboard dataset 93%

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

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%CC BY 4.0
prior · pull toward the middle▇▇ 7%
weighted average= 55.9

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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