Made To:Play with gender. This one was trained on ML generated images of single subjects with a wide variety of body types and complexions, with a focus on mixing masculine and feminine traits to produce new combinations.Specific trigger words were trained to make specific features or apply a general masculinity or femineity necessarily specifying a genders. Image styles ranged from highly realistic through anime/illustration, impressionist, pop art, etc.Model WeightsMost of the gallery images were between 0.2 - 0.6, depending on what checkpoint and other loras were used.Similar/Related LoRAs:<a target="_blank" rel="ugc" href="https://civarchive.com/models/264949/myriad">Myriad </a>was trained using a similar data set, but used auto-generated booru keywords to see how this would work using standard prompting.

Files with SHA256: 016724f0ad14f64db7e890669a4baeb721e5fa1bcaf335c77957aa1bbc704503