LoRAs

When using these LoRAs, it may be a better image to redraw only face or eyes using inpaint. Or, it is recommended to reduce the Weight of LoRA.

utsurome_v3.safetensors
- base model: 7th_anime_3.1_Cg
- training dataset: empty-eyes-dataset
yorime.safetensors
- base model: 7th_anime_3.1_Cg
shirome.safetensors
- base model: 7th_anime_3.1_Cg

utsurome_v3.safetensors

Sample Prompt

masterpiece, best quality, 1girl, empty eyes, utsurome, maid, smile
Negative prompt: (worst quality:1.4), (low quality:1.4), nsfw,
Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 416625012, Size: 512x768, Model hash: 49576e83ad, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: utsurome_v5(2f0093a7aa52), AddNet Weight A 1: 0.6, AddNet Weight B 1: 0.6

v3 has improved image quality compared to v2.

yorime.safetensors

Sample Prompt

masterpiece, best quality, 1girl, empty eyes, yorime, smlie, maid
Negative prompt: (worst quality:1.4), (low quality:1.4), (nsfw: 1.3), blush
Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 541777558, Size: 512x768, Model hash: 49576e83ad, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: yorime(5924d7962886), AddNet Weight A 1: 1, AddNet Weight B 1: 1

shirome.safetensors

Sample Prompt

masterpiece, best quality, 1girl, shirome, blank eyes,upper body,
Negative prompt: (worst quality:1.4), (low quality:1.4), (nsfw:1.3), blush, monochrome,
Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 266137625, Size: 512x768, Model hash: 49576e83ad, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: shirome(b89df5356523), AddNet Weight A 1: 1, AddNet Weight B 1: 1