I used official cutout character illustrations to train this LoRA. The base model is the animefull-final-pruned model. For a similar look to the original illustration: add 'small breasts' in prompt add 'loli' in negative prompt The example images were generated using merge model based on AbyssOrnageMix2 set this LoRA's weight to 0.4~0.8. my recommendation is 0.6. |