It's stable enough for me
Euler A or Euler.
CFG 5-7, I usually just use 7.
I usually upscale to 1536-2048 with 0.6 denoising to fix minor issues, then use Tile to upscale to 2048-2560+. If the low-res structure is fine, I directly Tile upscale to 2048+,My Tile parameters: strength 0.3-0.4, denoising 0.6-0.7,end at 0.7. If you only focus on portraits and upper body, slightly reduce the upscaling ratio. HadrianDeliceSDXL Workflow sample | Civitai

对我来说足够稳定了
Euler A 或 Euler
cfg 5-7，我一般就用7
我一般先放大到1536-2048，重绘幅度0.6来修复一些小问题，再用tile约束放大到2048-2560+，当然如果低分图的结构没什么问题也可以直接开tile放大到2048+，个人tile参数强度0.3-0.4，重绘幅度0.6-0.7，如果你只画肖像和上本身，请减小放大倍率 HadrianDeliceSDXL Workflow sample | Civitai

n-prompts:

(worst quality, low quality),deformed,distorted,disfigured,doll,poorly drawn,bad anatomy,wrong anatomy,sketch,jpeg artifacts,signature,watermark,artist name,old,oldest, white background, simple background

v2.0:

Conceptual enhancements have been made to the actions of wielding a katana, such as unsheathing.
Minor adjustments have been applied to the style of 'hungry clicker'

v1.4:

Adjust 4 artist styles:

Alicecrazy trigger word: alicecrazy style
Betabeet(Anon) trigger word: betabeet style
Ama Mitsuki (Ten Mitsuki) trigger word: ama_mitsuki_style_2024
Tnsk trigger word: tnsk style

本来我已经不打算在C站发模型了，因为我想保留一次警告次数，至少能在C站发个公告，发个动态，详情见我的文章。

不知道为什么这群老外只会盯着第一条警告辱骂我，我说了，我可以不发图，而且自从收到第一条警告，我也一直只发模型样图。

我郁闷的是有人在我的评论区发了P站链接，导致我被第二次警告。2024年还要付连带责任的？原来美国还是封建社会吗，笑死个人。况且我也没在任何管理制度中见到这一条。

过了几个月我也不想说啥了，还是有不少人找我，我就放出来吧。如果有一天我又莫名其妙的被ban了，来shakker(liblib)或者bilibili找我。