whatmodel.sh / image / Skywork UniPic 1.5B

Skywork UniPic 1.5B

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

Skywork UniPic 1.5B is an open-weights image model from Skywork AI, released July 2025. Its published size is 1.5B parameters. Licence: mit.

Catalogue identity notes

Skywork UniPic (v1) 1.5B autoregressive unified model (Skywork/Skywork-UniPic-1.5B, pinned 09991ea, MIT). WEAVE lists 'UniPic [68] 1.5B', the only UniPic v1 release. Comparison-only.

Model information sources

Release date ↗ · Weights licence ↗

1.5B as named by the maker.

39.9±6.3comparison 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 Skywork UniPic 1.5B, out of 197 with a score, then more from Skywork AI.

#modelscorewhereRAMreleased
145UniPic2-Metaquery-9B Skywork AI40±6comparison only2025-08
146Show-o2 1.5B-HQ Show Lab, NUS40±3local~7.9GB2025-06
147Skywork UniPic 1.5B Skywork AI40±6comparison only2025-07
148Stable Diffusion XL 0.9 (base) Stability AI40±6local~4.9GB2023-06
149Stable Diffusion 3 Medium Stability AI40±2api $0.035/image +local~11GB2024-06
more from Skywork AI
95UniPic 3 Skywork AI52±3comparison only2026-01
128UniPic2-SD3.5M-Kontext-2B Skywork AI44±6comparison only2025-08

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

$ what it's good at

other tests1 not in a task · 83% of its score
testresultvs the others in its rundifficultycountswhy
WEAVEBench in-context multi-turn editing (Avg)51.1% ✎█▄▄·▄▄▄▄█·▄█ beats 4/12medium · avg 65%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%at its level

$ where to run it

No verified API or download recorded yet · add one

Official weights and documentation: huggingface.co/Skywork ↗

$ how the score was worked out · WEAVE: Unleashing and Benchma… 83%

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
WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation (arXiv:2511.11434v1)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%CC-BY-4.0
prior · pull toward the middle▇▇▇▇▇ 17%
weighted average= 39.9

$ 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