Favorite art style (F社画风) | NoobAI x illu
详情
下载文件
关于此版本
模型描述
这是F社的画风LoRA,可以将其他画风的角色转换为F社画风。
使用我的LoRA时,请勿使用任何正面质量词。质量词的本质是画风,这也是为什么你的结果与我的差异极大,尤其是在光辉系列底模上!
Please do not use any positive quality tags when using my LoRA. The essence of quality tags is art style. This is why your results are so different from mine, especially on illu base model!
提醒:你需要关闭X和XXX可见才能看到我的全部LoRA。
This is a tip: you need to disable X and XXX visible to see all of my LoRA.
欢迎加入我的QQ群:514186900,答案是我训练过模型的一个角色的名字,她的英文名在群名中。
My Discord server: https://discord.com/invite/gVtk8XYWwt ←我的Discord服务器。
在爱发电为我买一份一美元炸鸡:https://afdian.com/a/YDDLJW
Tip me a one-dollar fried chicken: https://patreon.com/YDDLJW
————————————
V3.0:
由Noob XL V-pred训练的LoRA。使用后来的作品数据集替换了_星空的记忆_和_色鸟鸟_的训练集。
LoRA trained by Noob XL V-pred. The training sets of Hoshizora no Memoria and Irotoridori no Sekai were replaced with later works.
V2.1:
由Noob XL V-pred训练的LoHA,具有更强且更可控的表现力。
LoHA trained by Noob XL V-pred with more controllable and stronger performance.
network dim=16, conv dim=16
V2.0:
由Noob XL V-pred训练的LoHA,具有更可控的表现力。
LoHA trained by Noob XL V-pred with more controllable performance.
network dim=8, conv dim=8
V1.1:
128维版本,由NTR MIX训练。
Full 128 dim version, trained by NTR MIX.
V1.0:
32维版本,由NTR MIX训练。
Light 32 dim version, trained by NTR MIX.
————————————
触发词
favorite art,
————————————
对于V3.0:
推荐权重(Recommended weight):0~1.3(建议先试1)
————————————
对于V2.1:
推荐权重(Recommended weight):0~2.5(建议先试1.5)

————————————
对于V2.0:
推荐权重(Recommended weight):0~2.5(建议先试1.75)
————————————
推荐使用的底模(Recommended base model)
WAI-NSFW-illustrious-SDXL
(效果可能与展示图不同)(May have different performance than example post images)
/model/827184/wai-nsfw-illustrious-sdxl
NTR MIX | illustrious-XL | Noob-XL
(如果你是新手,建议先尝试这个)(Try this first if you're new here)
/model/926443?modelVersionId=1166878
WAI-SHUFFLE-NOOB
(普通Web UI请使用E预测版)(Please use E-pred version for general web UI)















