SDAS | Auxiliary model

Tips. 提示

⚠这个模型是AI辅助（画师）绘画推荐用A3.33,而非后续的版本⚠

⚠不建议用这个模型叠加LoRA使用，效果极差。但是你想用我也不拦着⚠

⚠不要问为什么别的模型能出这个模型不能出，你先看看你写没写或者写了什么奇怪的东西。⚠

——————————————

Intro. 简介

✔️A3.33是这个系列模型的基础，模型是使用5张AI生成的原始图像训练制得，底模使用ink_base。prem是A3.33的分支版本，训练方式大致相同，但是由于prem使用了A2.1H作为底模,其效果并不如ink_base

A3.33 is the basis of this series of models, which are trained using 5 original AI-generated images, with ink_base as the base model.Prem is the fork version of A3.33, training in much the same way, but because prem uses A2.1H as the base mode, the effect is not as good as ink_base

✔️SDHQ是由两个在ink_base上训练的模型融合而成（分别由3张图和7张图，图片均为AI生成），训练集采用尸块法处理。不过该模型在部分情况下存在过拟合问题。正因如此，您会有小概率直接看到训练集的内容或者固定的姿势。

This model uses the latest training methods,It is a merged of two models trained on ink_base(There are 3 pictures and 7 pictures respectively, all of which are generated by SD).And the training set was treated with Data Augmentation.This model has serious overfitting issues in some cases. That's why you have a small chance of directly seeing the content of the training set or the same posture.

——————————————

祝大家玩得开心＜3