CyberAIchemist
Update information
V3.0 updated. Fine-tuned LoRA to improve the effects of generating characters with complex body limbs and backgrounds. The overall styling is more toward manga style rather than simple lineart. A lower CFG scale can make lines thinner.
V3.0更新。对LoRA进行了微调，改善生成人物肢体和复杂背景的效果。整体更趋向漫画风而非纯线稿。低CFG scale可以让线条变细。
Recommend settings
Model: Anything V4.5
VAE: Orangemix (the same with NAI)
LoRA Strength: 1
Sampler: DPM++ 2M Karras
Sampling steps: 20
CFG: 7
Negative embedding: EasyNegative、badhandv4
Highres fix is also recommended.
Note: all the LoRA names used in sample images are my local name, you need to change them to your saved LoRA filename!
基模：Anything V4.5
VAE：Orangemix（同NAI）
LoRA强度：1
采样器：DPM++ 2M Karras
采样步数：20
CFG：7
负面embedding：EasyNegative、badhandv4
推荐使用高清修复。
注意：样图中的LoRA名称是我本地文件名，要改成你保存的文件名！
Difference
Here's a comparision of V2.0 and V3.0 (locally called V3 and V4 on my machine - V2 on my machine is not published):
V2.0和V3.0的对比（在我的本地机器上命名为V3和V4——本地的V2我并未发布）：
Comparision of different CFG scale:
不同CFG scale对比：
Popularity
Info
Version v1.0 offset: 1 File
About this version: v1.0 offset
Lineart style LoRA trained with offset noise, use monochrome or lineart to trigger, I highly recommend removing any color words from your prompt, like:
purple eyesblueflowerreddress
线稿风LoRA，使用时请添加monochrome 或lineart 开启。推荐将prompt中与颜色相关的单词去掉。
The demo images are generated w/ Anything V4.5 (orangemix VAE).
如何利用ControlNet提取线稿（using ContorlNet to extract linearts from illustrations）：https://www.bilibili.com/video/BV1Nv4y1a7ts
3 Versions
Go ahead and upload yours!
