v3.0 简约版，减少不必要的训练集，专注于抽象线条！该版本仅仅使用了4张训练数据训练而成，表现却极为优异，训练集不是使用成品图片而是使用“线”。这个合集都是别具一格的训练不同于常规训练方式训练而成的Lora，喜欢的话还请多多返图！触发词：lineart,multiple continuous regular lines,——————————— 使用和说明 ————————————1. CLIP终止层：1-4，大家不妨试试1或者4的效果，有惊喜！2.权重范围：0.2 至 1.5，建议使用0.7，1.1以上细节明显增多！XYZ示例图我分别用了三个大模型进行演示，分别是简约二次元，2.7D幻想以及写实大模型推荐使用“<a target="_blank" rel="ugc" href="https://www.liblib.ai/modelinfo/8c8f1c7f64d943ebb6b57833d5d042d2">lbc_Simple_简约</a>”或“<a target="_blank" rel="ugc" href="https://www.liblib.ai/modelinfo/76b421c56a3b43a8a300d01e040e6c37">lbc_Fantasy_幻想_2.7D</a>”或“<a target="_blank" rel="ugc" href="https://www.liblib.ai/modelinfo/669e2317673943828d861442f96619f0">lbc_Realistic写实</a>”大模型效果更佳。如果大家喜欢我训练的模型风格，还请多多支持！小弟感激不尽，如有想要训练的画风或角色也可以留言在下方，我可以免费为大家训练，一起分享美好事物！如果你有更好的建议请在评论区告诉我，或许你希望加入➡️<a target="_blank" rel="ugc" href="https://t.me/+npAVSiDrkPUzODVl">我的TG聊天频道</a>喜欢我的模型还请多多返图。

lbc_lineart

lbc_lineart_240403_v3.0.safetensors

v3.0

Line art_lbc Style

v3.0 Simplified Version, reduced unnecessary training data and focused on abstract lines! This version was trained using only 4 images, but its performance is extremely excellent, with no use of finished product images, but rather "lines". This collection is a unique training set that is different from regular training methods and is an Lora. If you like it, please give me plenty of likes! Trigger word: lineart, multiple continuous regular lines, ---------------------Below are introductions to other versions------------------------

Files with SHA256: e16e6dc04b6103cab309e7db1742088b83c90ad02f0645b151dc7d1d23b8af70