Some improvements over V5, mostly over the background and some details in the generation and in the light.
All of the images were generated using Clip Skip 2.
In negatives: ' (worst quality, low quality:1.4), ' OR ' (worst quality, low quality:1.4), (malformed hands:1.4),(poorly drawn hands:1.4),(mutated fingers:1.4),(extra limbs:1.35),(poorly drawn face:1.4), '
Doing smaller negative will help keep the creativity of the model, the longer negative will prevent it from that in exchange of a higher chance of getting good quality images in lower generations!