Comment by @simonj • Hey

There are two models. One SD 1.5 and one SDXL. The first one was trained with dreambooth. I think it was the LastBen GitHub. The SDXL (full checkpoint) was

Stats

Comments

For @lens/artbyjah and Aoife’s algorithms we don’t use the model trained on my film. They experimented with different SDXL models and eventually chose the ones that fit their vision best combined with individual prompting and settings that consist of fixed and variable parts and make the magic of their algorithms or ‘recipes’