Read the instructions first(Click to expand all instructions)

Goose Group:

Ink and Shadow Alchemy Pavilion-Taiqing Pavilion: 858495398

Ink and Shadow Alchemy Pavilion-Shangqing Pavilion: 764481772

Also, please follow my Xiaohongshu (Little Red Book) and Douyin (TikTok) accounts: yy469370733

This is a network-style flux-lora model, not a photographic model, focusing on high-p and high-blurring reverse realistic texture.

Online 1girl support + negative defaults on the LiBu online: ng_deepnegative_v1_75t, (badhandv4:1.2), EasyNegative, (worst quality:2), other parameters can also use the default parameters of flux on LiBu online, weight 0.8~1

Positive tags with  Ink and Shadow Artificial Human XL are universal, you can refer to the example image tags (applicable locally online)

Local parameters use the workflow in the example image, weight 0.9

The flux workflow used locally can refer to the example image or go to  Ink and Shadow-FLUX+SDXL-refiner image matrix  for download dev/fp8-document image.

This flux-lora model is labeled using  Ink and Shadow-GLM-4v-9b local tagger  If you are interested, feel free to download and try it.

If you think it's good, please support with more image returns, thank you~