whatmodel.sh / image / GLIDE (filtered)
GLIDE (filtered)
↗ share
+ contribute
GLIDE (filtered) is an open-weights image model from OpenAI, released December 2021. Its published size is 0.3B parameters. Licence: mit.
Catalogue identity notes
openai/glide-text2im small filtered-data model. Comparison-only: the official code runs from notebooks, with no single command or published memory figure.
Model information sources
300M = the GLIDE (filtered) base 64x64 text-conditional diffusion model as OpenAI states it; the separately released small filtered upsampler (no count given) is not included. Not the 3.5B unreleased full GLIDE.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of GLIDE (filtered), out of 197 with a score, then more from OpenAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 115 |  MetaQuery-XL | 47±6 | comparison only | ||
| 116 |  HiDream-I1-Full | 47±2 | api $0.050/image +local | ||
| 117 | GLIDE (filtered) | 47±15 | comparison only | ||
| 118 |  Ideogram 2.0 | 46±2 | api $0.080/image | ||
| 119 |  Infinity-8B | 46±5 | comparison only | ||
| more from OpenAI | |||||
| 1 | GPT Image 2.5 Sunburst | 92±2 | api $0.013/image | ||
| 2 | GPT Image 2.5 Flare | 88±2 | api $0.013/image | ||
| 3 | GPT Image 2 | 85±1 | api $0.053/image | ||
$ what it's good at
text to image▁▂▇▇▆▅█▇▂▃▁▁ #148 of 157 * · 6.1% of its score · 1 test
Trails CogView2, DALL·E Mega (minDALL-E), Versatile Diffusion v1.0 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| HPS v2 benchmark (4-style average) | 23.5% ✎ | ▃··▃▅·▅·▅▅█▅ beats 0/14 | 6.1% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: github.com/openai ↗
$ how the score was worked out · tgxs002/HPSv2 repository READ… 6%
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 |
|---|---|---|
 tgxs002/HPSv2 repository README, HPS v2 benchmark table | 1 | 6% |
| prior · pull toward the middle | 94% | |
| weighted average | = 46.5 |
$ 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