应@hit 要求制作了空和提纳里的lora。
有点抱歉，提纳里我记错成阿贝多了，因此提纳里的lora要稍微晚一两天了。
每个角色均使用1k+图训练。
新版本使用删标训练。
--
自Animagine XL V3出来后，对有无必要再训练Genshin Impact的角色，作者一直带有疑惑。
最终，作者还是决定顺从自己的内心。
每个角色均使用500张图片，训练了40epoch。
为了防止于A3自带角色冲突，没有使用触发词。
特别鸣谢：算力赞助 / GPU Sponsor: nieta.art
Based on https://civarchive.com/models/260267/animagine-xl-v3 training
Training model: Animagine XL V3
Inference model: Animagine XL V3
Training resolution: 1024*1024
Recommended output resolution: 1024*1280
Recommended model weight: 0.8~1
Description
FAQ
Details
Downloads
561
Platform
CivitAI
Platform Status
Available
Created
2/10/2024
Updated
5/13/2026
Deleted
-
Trigger Words:
tighnari \(genshin impact\)
black gloves,medal,hoodie,tassel,asymmetrical sleeves,yellow flower,black shirt,two-tone hair,turtleneck,wrist cuffs,
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.