_image38_batch3_v1-1678784318.jpeg)
V2 use 67 images ,more than v1 38 images.
warning: This LORA was train with only 38/67 images(v1/v2) because crawler couldn't find enough good data. So this model is not be great, will train again while enough train data.
Trigger Words in page,other tag in lora metainfo.
recommand use model: Kohaku_XL https://civitai.com/models/162577/kohaku-xl-beta
weight: 0.8~1
if not halo,please add “halo" to prompt