Version: v2.0

[Suggested to be used embedded with bad_pictures, easynegative]

======================================================

Sampling method: 2m karras or sde karras,

High-definition settings

Upscaling algorithm: 4x-ultrasharp

High sampling: 10

Redraw magnitude: <0.4

cfg scale: 2.5-6 (lower cfg for better realistic effect)

If the image pixels are too small or it's a full-body picture, you can use adetailer for facial retouching, and the inpaint denoising strength value is generally suitable ranging from 0.2 to 0.4.

======================================================

Copyright Notice: My model training uses sd-generated images for training. The uploaded model products shall not be used for digital models, reposting, or commercial purposes without my permission. In case the model is used for commercial purposes, all risks and liabilities are not associated with me, and I do not bear any legal responsibilities.