大家好,我是chosen鲷,这次给大家带来的是流光溢彩lora。
选了很多midjourney的那种很绚丽多彩的头像图片,作为训练集训练了这个lora,主要擅长出那种大头特写,色彩及其绚丽瞎眼,当然了,如果想要作为一种画风来出全身图乃至于场景图也可以,他的兼容性不错,推荐权重0.7-1。推荐的tag
(masterpiece:1.2), best quality,PIXIV,Colorful portraits, multicolored,
这里写你想要的内容
<lora:Colorful portraits_20230715165729-000018:1>
Negative prompt: EasyNegative, badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2871530726, Size: 800x400, Model hash: 10ddbe9326, Model: Chosen Starry sky, Denoising strength: 0.5, Clip skip: 2, ENSD: 31337, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+ Anime6B
大模型方面跟ghost绝配, 其余的像我的 chosen mix,irises,impasto,都可以,常见的majic,meina等等的也都有很好的适配性,大家自己去尝试吧。
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。
Description
FAQ
Comments (1)
Very good idea, but probably a bit overtrained, especially on hair. It changes too much the hair, every girls have the same curly hair with this Lora
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.












