whatmodel.sh / image / AttnGAN (COCO)
AttnGAN (COCO)
↗ share
+ contribute
AttnGAN (COCO) is an open-weights image model from Microsoft / Rutgers / Duke, released November 2017.
Catalogue identity notes
TIFA Appendix E AttnGAN row; original COCO text-to-image system.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of AttnGAN (COCO), out of 197 with a score.
| # | model | score | where |
|---|---|---|---|
| 193 |  LCM Dreamshaper v7 | 23±4 | local |
| 194 |  InstructPix2Pix | 19±3 | local |
| 195 |  X-LXMERT | 17±4 | comparison only |
| 196 | AttnGAN (COCO) | 16±4 | comparison only |
| 197 |  CogView2 | 1±4 | local |
$ what it's good at
text to image▃▂▇▇▆▅█▇▂▃▁▁ #157 of 157 * · 94% of its score · 1 test
Trails CogView2 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| TIFA v1.0 (overall, mPLUG VQA) | 58.1% ✎ | █·······▄▄▄▄ beats 0/5 | 94% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: github.com/taoxugit ↗
$ how the score was worked out · TIFA: Accurate and Interpreta… 94%
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 |
|---|---|---|
 TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering (arXiv v3) | 1 | 94% |
| prior · pull toward the middle | 6% | |
| weighted average | = 16.2 |
$ 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