这是画师Anmi的画风LoRA.
在使用我的LoRA时请不要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和我的差别很大，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!
这是一个提醒：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.
欢迎来我的Q群玩：514186900，答案是我炼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lokr，拥有最佳的表现。
Lokr trained by Noob XL V-pred with best performance.
V2.0：
由Noob XL V-pred训练的LoHA，拥有更可控的表现。
LoHA trained by Noob XL V-pred with more controllable performance.
V1.0：
Noob XL V-pred训练的LoRA.
LoRA trained by Noob XL V-pred.
————————————
触发词（Trigger tag）
AnmiStyle,————————————
For V3.0：
推荐权重（Recommended weight）：0~1.2 (try 1 first)
————————————
For V2.0：
推荐权重（Recommended weight）：0~2 (try 1.5 first)
————————————
推荐使用底模（Recommended base model）
WAI-NSFW-illustrious-SDXL
（效果也许和展示图不同）(May have different performance than example post images)
https://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl
NTR MIX | illustrious-XL | Noob-XL
（如果你是新手，先试试这个）(Try this first if you're new here)
https://civarchive.com/models/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)
Description
Lokr trained by noob xl v-pred
FAQ
Comments (5)
QQ群炸了（挠头）
It seems that this lora is not working well with NAI Vpred model, but works well on WAI...?
any examples?
wai shuffle noob used in posts is a nai vpred model
@YDDLJW https://imgur.com/a/3evXpLl
Following you instructions, no quality tags, only your lora, running on NoobAI VPred1.0 Model, using ComfyUI
@QR0W_
i think this one needs hires fix though, but still weird... actually i never check my model's performance on my training base model original noob xl vpred... maybe just use it on other fine-tuned base model.
and i just found that noob xl vpred work better with only "euler" but not "euler a", also weird