kisaragi mix is a stable-diffusion checkpoint model developed by the Google AI research team. stable-diffusion is a type of generative model that can generate images from noise. A checkpoint model is a trained model that is saved at a certain point in time, and by loading this model, you can resume learning from the state at that point.
kisaragi mix was developed with the aim of capturing the characteristics of traditional Japanese bijinga. Therefore, the images generated from this model have the following characteristics:
big eyes and high nose
thin eyebrows and long eyelashes
fair skin
soft hair
Traditional Japanese costumes such as Japanese clothes and kimonos
