Help fuel my passion! Even $1 makes a difference.
该模型仅使用超过400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，得到纯净的高桥留美子的风格LORA。
Flux版本：https://civarchive.com/models/845756
Animagine XL和 SD1.5 版本：https://civarchive.com/models/142487
--- --- --- --- --- --- --- ---
This model used more than 400 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
Flux version：https://civarchive.com/models/845756
Animagine XL and SD1.5 version：https://civarchive.com/models/142487
Description
FAQ
Comments (10)
非常棒的风格，就不知道高桥老师的作品重置能不能继续以《新福星小子》这种优质风格重置下去了♥
大佬你的lora太棒了，会有平井久司风格的lora吗
这个社区里太多了，搜高达seed之类的关键词就有一堆了
This is a well crafted Takahashi Rumiko style lora. I use it at lower weights to keep my style but get the characters, and it handles well. 5 Star Lora highly recommend.
牛B，yyds，出图率太高了，大佬真的是满足童年心愿了
I've really enjoyed using this model with Illustrious. Any odds of it being ported to ZImage-Turbo?
The current ZImage-Turbo is not very suitable for anime or comic style(2D), and will be judged according to the actual situation in the future, if the effect is great, then the lora ecosystem will naturally be migrated to ZImage-Turbo.
@flyx3 Fair enough, I've been getting some decent results in it just because of how good it is at prompt adherence, and using that as input into this model instead, but if you think it's not suitable, well, it's a matter of time until something better comes along.