realgirlmix3
融合改进了我个人其他模型,改善了半身以上的光影,使得光影更加具有层次感,增加了出图的暖色调,并改善了面部脸型。
实测对于近身面部细节的真实化更强。
在线生成麻烦用实际tag不要用嵌入式。
可以再本地使用(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,badhandv4,ng_deepnegative_v1_75t,
一定要开高清修复,一定!!!
支持768x768的出图能力
下面推荐参数是我复制原模型的,通用
推荐参数:
•vae:已经嵌入vae-ft-mse-840000-ema-pruned 、
•采样:DMP++SDE Karras(强烈推荐) ,1.6新采样器也可尝试
•步数:35
•高分辨率修复:20步
•放大算法:4x-UltraSharp、8x_NMKD-Superscale_150000_G等搭配使用。
•重绘幅度:0.2
•放大倍数:1.5倍以上。
Realgirlmix3
Integrating and improving my other personal models, improving the light and shadow above the body, making the light and shadow more layered, adding warm tones to the drawing, and improving the facial shape.
The actual measurement has stronger realism for close up facial details.
Please use actual tags instead of embedded ones for online generation.
Can be used locally (best quality: 2), (low quality: 2), (normal quality: 2), lowres, watermark, badhandv4, ng_ Deepnegative_ V1_ 75t,
Make sure to open high-definition repair, make sure!!!
Supports 768x768 graphics capability
The following recommended parameters are for me to replicate the original model, universal
Recommended parameters:
• Vae: already embedded in vae-ft-mse-840000-ema run
Sampling: DMP++SDE Karras (strongly recommended), 1.6 new samplers can also be tried
Steps: 35
High resolution repair: 20 steps
Amplification algorithm: 4x UltraSharp, 8x_ NMKD Superscale_ 150000_ Used in combination with G.
Redraw amplitude: 0.2
Magnification: 1.5 times or more.