CFG: 2.5! Too high CFG will cause explosion! [Hint word guide coefficient cfg scale]Note: CFG is associated with reverse hint words (low quality:2) with equal weight. Increasing CFG requires appropriately reducing the weight of reverse hint words.*1.5 The highest definition on the entire network, based on image algorithm-optimized direct output examplesWhen I output the images locally, I added some post-processing algorithms to make the images more interesting, which may result in some differences from other users when they are generating images."This algorithm mainly makes the image clearer, with a larger color gamut, and better details in the dark areas" — but these effects are unrelated to the model itselfVersion: v4Sampling method (Sampler): Euler KarrasUpscaling algorithm: 4x-UltraSharpSampling iteration steps (Steps): 20-30HD restoration sampling times: 0-10Redraw amplitude (Denoising): 0.2-0.4Width 512, Height 768Hint word relevance (CFG Scale): 2.5======================================================QQ group: 852450267======================================================建议CFG: 2.5！CFG高了会炸！【提示词引导系数 cfg scale】注意：CFG 关联反向提示词的(low quality:2)等权重。提高CFG需适当降低反向提示词权重*1.5全网最高清，基于图像算法优化的直出样例我在本地出图的时候加入了一些后处理算法让画面的表现更有意思，这会导致与其它用户在生图的时候有一些差异，「这个算法主要使画面变得更清晰，色域更大，暗部细节更好」——但这些效果与模型本身无关版本：v4采样方法(Sampler)： Euler Karras放大算法：4x-UltraSharp采样迭代步数(Steps)：20-30高清修复采样次数：0-10重绘幅度(Denoising):0.2-0.4宽度 512，高度 768提示词相关性(CFG Scale): 2.5======================================================我的交流群：QQ 852450267======================================================版权说明：我的模型训练使用SD生图进行训练，所上传的模型成品在本人未允许的情况下不得用于数字模特、转载及搬运等商业用途。如果在商业用途中使用了该模型，那么一切风险与责任追究与本人无关，本人不承担任何法律责任！Copyright note: My model training uses SD graphics for training, the uploaded finished model shall not be used for digital modeling, reprinting and handling without my permission. If the model is used in commercial use, then all risks and liability have nothing to do with me, I do not bear any legal responsibility!

kimchiMix

kimchimix_kimchibabyRealistic.safetensors

kimchiBaby_realistic_v2

v4.0

kimchiMix_v3.0

kimchiBaby_v1.1

kimchiBaby_v1

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: &lt;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.

kimchiBaby_realistic_v2.fp16.safetensors

v2.0

v2.5

v3.25 (Special Edition)

Files with SHA256: 9c510cc0987d4047ae1eb1d367020249252fb89414401bd24d3926c0b99655e3