Type
LORA
Publish Time
2023-10-11
Base Model
SD 1.5
Version Introduction
用了不同的训练集训练出了这个版本,没用1.0版本的过拟合,色彩偏亮,背景色彩会有渐变效果







推荐与CuteYukiMix、betterMix_Anime等可爱风格模型使用
推荐参数:
Sampler: Euler a & DPM++ 2M Karras
Sampling steps: 3>
CFG scale: 7
推荐高分辨率修复参数:
Upscaler: R-ESRGAN 4x+ Anime6B
highres steps: 0
Denoising: 0.5
推荐权重:0.7以下!!!
推荐Negative prompt: bad-artist-anime
希望各位玩的开心~
用了不同的训练集训练出了这个版本,没用1.0版本的过拟合,色彩偏亮,背景色彩会有渐变效果
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
