This is trained on the same dataset from version 1.1, but single photos were added instead of only the side-by-side images. This version may be over-trained, so try dialing back the weight depending on what base model you are using. Here are some sample captions that were used during training:
Photo of a ????? woman with blonde hair. She has small ???????. There is ??? dripping off of her mouth and chin and on to her ?????. She has hard nipples.
Photograph of a woman with dark hair and an open mouth. She is pushing her ??????? together with her hands. Her ??????? are pierced. She has ??? on her right ??????. She is in a bedroom and sitting on a bed. She has medium sized breasts.
Photograph of a ????? woman laying on a white bed. She has ??? on her small ??????? and inbetween her ???????. Her ??????? are hard. She has light brown hair. Her mouth is open.
Close up photograph of a woman's ?????. Trimmed pubic hair. ??? is dripping out of the ??????? opening and onto the bed.
Close up photograph of a woman's face covered in ???. ??? on her cheeks. ??? on her lips. ??? on her chin. Shoulder length dark hair. Wearing eye shadow and dark eye liner.
You can download the dataset and see the captions and images for yourself.
