基于NAI底模训练的青雀角色lora,服装还原度良好,换装以及较为容易
使用方法:
推荐权重:0.7~0.9,建议使用高清修复
核心触发词:1girl, official, green eyes
如果需要换装则不使用official并降低权重
translate by GPT:
Based on NAI training, the model of the Honkai Star Rail character, Qingque.
The accuracy of clothing replication is good, and it's relatively easy to or create content.
Instructions:
Recommended weight range: 0.7~0.9. High-definition restoration is suggested.
Core trigger words: 1girl, official, green eyes
If you want to create an image of the character or in different clothing, don't use "official" as a trigger word and lower the weight range.
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
