
This is a style LORA aimed at recreating the art style of Nai3 on Flux, and I used Nai3 to generate nearly 400 high-quality images as the training set. Currently, this lora is still in the experimental stage and might have some issues, if you encounter any problems during use, feel free to let me know in the comments section!
这个lora是一个画风lora,目的是在flux上重现Nai3的艺术风格,我使用Nai3生成了接近400张高质量的图片作为训练集,目前这个lora尚属于实验版本,可能会有一些问题,如果你遇到任何使用上的问题,欢迎在评论区告诉我!
***Please make sure to add the trigger word "nai3_style_for_flux".
***请务必添加触发词nai3_style_for_flux
I recommend adding the following quality prompts. Based on my testing, they can make the art style more closely resemble the style in the training set:
我推荐加上如下这段质量提示词,经过我的测试,它可以让画风更加接近训练集中的画风:
detailed, dramatic lighting, realistic,detailed,natural lighting,photorealistic,authentic,crisp details,breathtaking scenery,(masterpiece:2),best quality,ultra highres,original,extremely detailed,perfect lighting,Cinematic Lighting,highres,photo_(medium),vibrant colors,surreal,trippy,
I recommend setting flux guidence/Distilled CFG Scale around 3.5 and using Euler+Simple
我推荐将flux guidence/Distilled CFG Scale设置在3.5左右,使用Euler simple采样器
描述:
训练词语: nai3_style_for_flux
名称: nai3_for_flux.safetensors
大小 (KB): 299478
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success