Type | |
Stats | 6,249 42,330 |
Reviews | |
Published | May 10, 2024 |
Base Model | |
Training | Steps: 12,360 Epochs: 5 |
Usage Tips | Clip Skip: 2 |
Trigger Words | yuuki rito lala satalin deviluke nana asta deviluke momo velia deviluke haruna sairenji yuuki mikan konjiki no yami kotegawa yui kurosaki meia run elise jewelria +7 more |
Hash | AutoV2 B796C727AD |
该模型使用了超过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，得到纯净的矢吹健太朗风格LORA。
FLUX版本：https://civitai.com/models/712970
Animagine XL V3版本：https://civitai.com/models/275386
illustriousXL 版本：https://civitai.com/models/892124
Neta Art XL版本：https://civitai.com/models/463454
SD1.5版本：https://civitai.com/models/136677
可以使用以下角色提示词：
结城梨斗 yuuki rito,
夕崎梨子 yuusaki riko,
菈菈 lala satalin deviluke,
娜娜 nana asta deviluke,
梦梦 momo velia deviluke,
西连寺春菜 haruna sairenji,
结城美柑 yuuki mikan,
金色之暗伊芙 konjiki no yami,
古手川唯 kotegawa yui,
黑咲芽亚 kurosaki meia,
露恩 run elise jewelria,
---
XL_V2.0新增以下角色提示词：
天条院沙姬 Tenjiuin Saki,
雾崎恭子 Kirizaki Kyoko,
御门凉子 Ryuko Mikado,
提亚悠·鲁娜提克 Tearju Lunatique,
涅墨西斯 Nemesis,
籾冈里纱 Momioka Risa,
九条凛 Kujou Rin,
--- --- --- --- --- --- --- ---
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://civitai.com/models/712970
Animagine XL V3 version：https://civitai.com/models/275386
illustriousXL version：https://civitai.com/models/892124
Neta Art XL version：https://civitai.com/models/463454
SD1.5 version：https://civitai.com/models/136677
One more thing：
Pony Diffusion V6 XL is an excellent base model, but for the two-dimensional animation style (2D), the biggest disadvantage is that it cannot stably output the specified style, and it is always somewhat realistic in terms of color.