Image generation models in 2022
13
Models
10 organisations
25%
Open weights
3 open, 9 closed
0
Frontier
By Epoch's flag
20B
Largest traceable
Parti
2022
Span
4 with a traceable size
Releases
by monthOrganisation
Records
13| Model | Organisation | Released | Parameters | Weights |
|---|---|---|---|---|
| AR-LDM | Alibaba | 2022-11 | 2B | Closed |
| Discriminator Guidance | Korea Advanced Institute of Science and Technology (KAIST) | 2022-11 | — | Open |
| DiT-XL/2 + Discriminator Guidance | Korea Advanced Institute of Science and Technology (KAIST) | 2022-11 | — | Closed |
| eDiff-I | NVIDIA | 2022-11 | 9B * | Closed |
| Diffusion-GAN | UT Austin | 2022-06 | — | Open |
| Parti | Google Research | 2022-06 | 20B | Closed |
| Imagen | Google Brain | 2022-05 | 8B * | Closed |
| DALL·E 2 | OpenAI | 2022-04 | 4B * | Closed |
| Stable Diffusion (LDM-KL-8-G) | Runway | 2022-04 | 1B | Open |
| XMC-GAN | Google Research | 2022-04 | — | Closed |
| Make-A-Scene | Meta AI | 2022-03 | 4B * | Closed |
| MaskGIT (ImageNet) | Google Research | 2022-02 | 227M | Not recorded |
| Midjourney V1 | Midjourney | 2022-02 | — | Closed |
An asterisk marks a parameter figure the source does not consider traceable to the people who built the model. That judgement is the source’s and it has false negatives: Kimi K3 is marked speculative at 2.8T while Moonshot’s own model card states the figure. Why that distinction carries the whole exhibit.
Counts are of models Epoch AI records as notable, not of every model released. The most recent month is always incomplete, because a model enters the dataset when it is reviewed rather than when it ships.
Epoch AI, 'Data on AI Models'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/data/ai-models-documentation' Used under CC BY 4.0.