This model was originally uploaded to HuggingFace / Civitai. If it's yours, please contact us so we can transfer it to your account!
感谢 40原 老师的原画
https://www.pixiv.net/users/554102
该训练使用了秋叶大佬的 lora-script 进行训练
https://github.com/Akegarasu/lora-scripts
训练时使用了 loCon，故最好将模型放在 ./models/lora 文件夹里，在 prompt 中使用 <lora: 模型名: 权重> 的语法进行使用。
经过验证，第 12 epoch 的效果最好，所以使用了该 epoch 的模型。
【例图】
通用参数生成，强烈建议使用 DPM++2S a Karras 采样。出图的底模：
https://civitai.com/models/7189/school-anime
（电脑太慢了，就不使用其它模型来测试了）
【注】请勿将该模型用于商用！
Download (14.2 MB)
Download available on desktop only
🙈 Heads up! This is not an AI model, but a model addon. This file doesn't produce images by itself – it needs to be used in combination with one of our image AI models. Learn how to do it with our crash course.
Popularity
340
100
Info
Version v 0.1: 1 File
40_v01.safetensors
(14.2 MB)
To download these files, please visit this page from a desktop computer.
About this version: v 0.1
训练的数据和其它 epoch 的模型可在以下链接获取：
1 Version
😥 There are no 40原老师家的猫猫 v 0.1 prompts yet!
Go ahead and upload yours!
