whatmodel.sh / image / UniPic2-SD3.5M-Kontext-2B
UniPic2-SD3.5M-Kontext-2B
↗ share
+ contribute
UniPic2-SD3.5M-Kontext-2B is an open-weights image model from Skywork AI, released August 2025. Its published size is 2B parameters. Licence: mit.
Catalogue identity notes
Skywork UniPic 2.0 editing/generation model on SD3.5-Medium with Kontext-style conditioning, 2B (Skywork/UniPic2-SD3.5M-Kontext-2B, pinned c64315f, MIT). WEAVE 'UniPic2-SD3.5M [73] 2B'. A separate -GRPO-2B repo exists; WEAVE's label has no GRPO suffix, so the base release is mapped. Comparison-only.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of UniPic2-SD3.5M-Kontext-2B, out of 197 with a score, then more from Skywork AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 126 |  FLUX.1 Kontext [dev] | 44±1 | api $0.025/image +local | ||
| 127 | FLUX.1 [dev] | 44±1 | api $0.025/image +local | ||
| 128 | UniPic2-SD3.5M-Kontext-2B | 44±6 | comparison only | ||
| 129 |  UNO | 43±4 | local | ||
| 130 |  ChronoEdit-14B | 43±3 | local | ||
| more from Skywork AI | |||||
| 95 | UniPic 3 | 52±3 | comparison only | ||
| 145 | UniPic2-Metaquery-9B | 40±6 | comparison only | ||
| 147 | Skywork UniPic 1.5B | 40±6 | comparison only | ||
$ what it's good at
other tests1 not in a task · 83% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| WEAVEBench in-context multi-turn editing (Avg) | 56.8% ✎ | █▄▄·▄▄▄▄█·▄█ beats 6/12 | 83% |
$ 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
| source | results | share of the score |
|---|---|---|
 WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation (arXiv:2511.11434v1) | 1 | 83% |
| prior · pull toward the middle | 17% | |
| weighted average | = 44.0 |
$ 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