version 5, applying more of its own stylization to images, while the 5.1 RAW model adds improvements while working better with more literal prompts. The version 5.2 included a new "aesthetics system", and the ability to "zoom out" by generating surroundings to an existing image. On December 21, 2023, the alpha iteration of version 6 was released. The model was trained from scratch over a nine month period. Support was added for better text rendition and a more literal interpretation of prompts.

| style="vertical-align: top;" |

:|}

1.Previous
3.Next