v8.0:增强了写实风格
v8.0: Enhanced the photorealistic style
3.0所有示例图片都是ComfyUI默认工作流直出没有放大和修正
参数为:
3.0 All sample images are ComfyUI default workflows straight out without enlargement and correction
The parameters are:
分辨率:1024 x 1536
采样器:Euler
Steps: 25, CFG scale: 5,
832 x 1216
采样方法 (Sampler):Euler a
迭代步数 (Steps):28
CFG:7.5
masterpiece, best quality, very aesthetic, latest,
worst quality, low quality, jpeg artifacts, 3d, multiple views, 4koma, bad anatomy, bad hands, text,
使用了4个illustriousXL模型进行融合并融入了自己训练的Lora
合并的模型分别是:
Four illustriousXL models were used to fuse and incorporate Lora, which was trained by itself
The merged models are:
Illustrious-XL
PaSanctuary (SDXL, IllustriousXL)
Illustrious-XL SmoothFT
illustrious_pencil-XL
Description
FAQ
Comments (9)
It will remain at version 7.0 even though there will be no future updates.
老哥牛逼!!!模型是真好看
add model in https://www.seaart.ai/ pls
模型好的是真的好啊,是我最近遇到的最棒的,玩好长时间了,但过度真实,我P站号直接没了,哭唧唧——奉劝各位,哥们的账号祭天,让大家吸取惨痛的教训…………呜呜呜呜~
啊,受不了了baby,你快把我身体掏空了😂,还有比V8版本更好的吗baby
老哥太厉害了吧
大佬这个模型很不错,我就喜欢这个皮肤质感,但是这个模型不能融合,2.5d国风人物就不怎么像,能不能出一个能融合的
非常棒的模型,特别是v8
v8写实部分相当厉害




