whatmodel.sh / image / Show-o2 1.5B
Show-o2 1.5B
↗ share
+ contribute
Show-o2 1.5B is an open-weights image model from Show Lab, NUS, released June 2025. Its published size is 1.5B parameters. Licence: apache-2.0.
Catalogue identity notes
Comparison-only, proposed so the Show-o2 paper's GenEval and DPG-Bench runs hold two own models. The paper's 'Show-o2 (Ours) 1.5B' rows are the base 1.5B model (66M training pairs); the catalogued Show-o2 1.5B-HQ is the later higher-resolution checkpoint and is not the paper row. Weights: https://huggingface.co/showlab/show-o2-1.5B (sha 07ec16589d4fc5422a74dddbbc4b2cd11e551039, created 2025-06-05, apache-2.0); listed on the official README among the released Show-o2 models.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Show-o2 1.5B, out of 197 with a score, then more from Show Lab, NUS.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 121 |  Midjourney V6 | 45±7 | comparison only | ||
| 122 |  Gemini 2.0 Flash Image Generation (preview) | 45±2 | comparison only | ||
| 123 | Show-o2 1.5B | 45±5 | comparison only | ||
| 124 |  DeepGen 1.0 | 45±3 | comparison only | ||
| 125 |  DALL·E 3 | 44±1 | comparison only | ||
| more from Show Lab, NUS | |||||
| 138 | Show-o2 7B | 42±3 | local | ||
| 146 | Show-o2 1.5B-HQ | 40±3 | local | ||
| 159 | Show-o (show-o-demo-512) | 36±3 | local | ||
$ what it's good at
text to image▁▂▇▇▆▅█▇▂▃▁▁ #93 of 157 * · 89% of its score · 2 tests
Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ) here, though they rank higher overall.
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/showlab ↗
$ how the score was worked out · Show Lab Show-o2 paper (arXiv… 89%
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 |
|---|---|---|
 Show Lab Show-o2 paper (arXiv:2506.15564v3), GenEval and DPG-Bench tables (own models) · lab-reported | 2 | 89% |
| prior · pull toward the middle | 11% | |
| weighted average | = 44.8 |
$ 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