Type
LORA
Publish Time
2023-11-05
Base Model
SD 1.5











尝试了另外几个其他作者的早期迪丽热巴lora,我自己做出来不太像,就自己训一个。
训练底模:墨幽的姐姐——墨幽岚_v1
采样步数:30-50
采样方法:Restart>DPM++ 2M Karras>DDIM
CFG:7
放大算法:4xUltrasharp
放大步数:15
重绘幅度:0.2
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
