whatmodel.sh / image / JoyAI-Image-Edit

JoyAI-Image-Edit

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

JoyAI-Image-Edit is an open-weights image model from JD (JoyAI), released March 2026. Licence: apache-2.0.

Catalogue identity notes

JD Joy Future Academy's JoyAI-Image-Edit (jdopensource/JoyAI-Image-Edit, pinned 20af57b, Apache-2.0; created 2026-03-31). Edit-Compass 'JoyAI-Image-Edit Joy Future Academy (2026)'. The later JoyAI-Image-Edit-Plus is a different model and is not assumed. Comparison-only.

Model information sources

Release date ↗ · Weights licence ↗

56.7±2.9comparison only: no current run option verifiedfrom 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 JoyAI-Image-Edit, out of 197 with a score.

#modelscorewhereRAMreleased
68HunyuanImage 3.0 Tencent57±2api $0.080/image +local~49GB2025-09
69Emu3.5 BAAI57±5local~85GB2025-10
70JoyAI-Image-Edit JD (JoyAI)57±3comparison only2026-03
71MAI-Image-1 Microsoft AI57±3comparison only2025-11
72LongCat-Image-Edit Meituan56±2api $0.15/image +local~36GB2025-12

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

$ what it's good at

image to image / editing▁▁▁▃▂▃█▃▃▃▁▁ #45 of 81 * · 96% of its score · 1 test

Beats Imagen 4, GPT Image 1 Mini, FLUX.2 [dev] here, though they rank higher overall. Trails FLUX.2 [klein] 9B, LongCat-Image-Edit here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Edit-Compass (EN, overall)53.6% ✎▃▃▂·▃▆▂█·▃·▃ beats 15/20hard · avg 45%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%at its level

$ where to run it

No verified API or download recorded yet · add one

Weights and documentation: huggingface.co/jdopensource ↗

$ how the score was worked out · Edit-Compass & EditReward-Com… 96%

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
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%CC-BY-4.0
prior · pull toward the middle▇ 4%
weighted average= 56.7

$ 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