大家好,我是chosen鲷,好久不见。
因为试用了noobai感觉非常好用,于是尝试用这个模型作为底膜训练了lora,头一次训练xl的lora,属于是半尝试性质的,感兴趣的朋友可以试一试。后续打算以这个为底膜训练一些喜欢的角色。然后把之前的一些喜欢的风格lora训练一下XL版本。
触发词Korean impasto style,权重建议0.6-0.8,适合做韩风厚涂立绘风格,可以自行尝试。
具体的tag可以看我例图。
大模型要用用noobai 0.5版本(下方推荐)
感谢大家的下载使用,如果喜欢的话欢迎关注我,我的bilibili pixiv ID均为chosen鲷,欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0,https://www.pixiv.net/users/40911695 谢谢。
The following content is from Google Translate
Hi, I'm chosen鲷, long time no see.
Because the trial noobai feel very good, so try to use this model as the bottom film training lora, the first training xl lora, is a semi-trial nature, interested friends can try. In the future, I plan to use this as the base film to train some favorite characters. Then take some of the previous favorite styles lora training XL version.
Trigger word Korean impasto style, weight is recommended 0.6-0.8, suitable for Korean thick painting style, you can try yourself.
The specific tag can see my example diagram.
Use noobai version 0.5 for large models (recommended below)
Thank you for downloading and using, please follow me if you like, my bilibili pixiv ID is chosen Snapper, Welcome to focus on my channel, https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0, https://www.pixiv.net/users/40911695, thank you.
Description
FAQ
Comments (3)
终于又开炉了啊。NoobAI的话应该算Illustrious底模吧。
https://civitai.com/models/833294?modelVersionId=1022833 上有人回答了:Illustrious是noob的基础模型,noob由于大刀阔斧的训练,和Illustrious有许多不同,训练在Illustrious上的lora虽然可以在noob上工作,但是效果不完美,我个人认为Illustrious的lora中角色Lora的效果好于画风Lora
0.5的E-pred NoobAI还是被LAX视为Illustrious的。
嗯,对的,是光辉模型。我前一阵子还想找你问问noobai的事来的,结果在b站搜半天绽青节点,怎么都搜不到,后来有一天突然想到,那个字好像念砚yan来的。



















