whatmodel.sh / image / Infinity-8B
Infinity-8B
↗ share
+ contribute
Infinity-8B is an open-weights image model from ByteDance (FoundationVision), released February 2025. Its published size is 8B parameters. Licence: mit.
Catalogue identity notes
ByteDance FoundationVision's Infinity bitwise autoregressive text-to-image model, 8B 1024px weights (FoundationVision/Infinity, folder infinity_8b_weights; pinned e710892, MIT; GitHub news 'Feb 18, 2025: Infinity-8B Weights & Code is released!'). MMMG Table 2 lists 'Infinity' at 1024 px and its later analysis names the same model 'Infinity-8B'; the repo's other 8B folder is a 512x512 middle-stage model (Jun 2025), so the 1024 px row is the main 8B release. Not mapped: ImagenWorld, WISE Table 11 and HPSv3 'Infinity' rows (2B vs 8B not stated). Comparison-only.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Infinity-8B, out of 197 with a score.
| # | model | score | where |
|---|---|---|---|
| 117 |  GLIDE (filtered) | 47±15 | comparison only |
| 118 |  Ideogram 2.0 | 46±2 | api $0.080/image |
| 119 | Infinity-8B | 46±5 | comparison only |
| 120 |  FLUX1.1 [pro] | 46±2 | api $0.040/image |
| 121 |  Midjourney V6 | 45±7 | comparison only |
$ what it's good at
text to image▁▂▇▇▆▅█▇▂▃▁▁ #91 of 157 * · 88% of its score · 1 test
Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ) here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MMMG knowledge-image generation (MMMG-Score, average over education levels) | 19.2% ✎ | ▃··▃·█▃▃▅··▃ beats 8/9 | 88% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: huggingface.co/FoundationVision ↗
$ how the score was worked out · MMMG: A Massive, Multidiscipl… 88%
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 |
|---|---|---|
 MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning (arXiv:2506.10963v2) | 1 | 88% |
| prior · pull toward the middle | 12% | |
| weighted average | = 46.0 |
$ 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