该模型使用了超过100张高质量的原始图片。
训练图片全部来自该画师的原画集,TV版动画图片素材没有混入其中,得到纯净的兰宫凉风格LORA。
illustrious XL版本:https://civarchive.com/models/1550901
Animagine XL V3版本:https://civarchive.com/models/455768
碎碎念:(仅中文)
Pony的风格稳定性问题真的是无力吐槽,随处可见的元素冲突,想追求还原度的还请移步隔壁Animagine XL V3版本的lora吧。 ╮(╯▽╰)╭
--- --- --- --- --- --- --- ---
This model used more than 100 high-quality original pictures for training.
The training pictures are all from the original painting collection of the artist, and the TV version animation picture materials are not mixed in, so as to obtain the pure artist style LORA
illustrious XL version:https://civarchive.com/models/1550901
Animagine XL V3 version:https://civarchive.com/models/455768
Description
FAQ
Comments (2)
对比了下AnimgineXL, 确实看出pony出的线条不稳定了......有种乱乱的感觉
所以还是别训pony版本了,改为训个Neta Art XL版本看看效果吧 w:https://civitai.com/models/410737/neta-art-xl







