本页面包含 MOSS 和 Anima 两个版本，请选择对应的使用说明。
This page includes both MOSS and Anima versions. Please follow the instructions for your model.

_______________________________________________________________________________________

推荐参数/Recommended Settings

FOR ANIMA:

• 触发词/Trigger word: @ttaistyle

• 权重/Recommended weight:0.7~1

• Sampler: er_sde + beta OR euler + normal

• CFG:4

• STEPS:30

FOR MOSS：

复杂场景，请提高CFG和步数，SFT例外。For complex scenes, increase the CFG and sampling steps,except when using SFT.

• 触发词/Trigger word: @ttaistyle

• 权重/Recommended weight:1~1.2

• Sampler: er_sde + beta OR euler + simple

• CFG:3-5

• STEPS:30-50

____________________________________________________________________________________

MOSS

V1.1

• 和ANIMA同数据集训练，感觉依然欠拟合，我大概会再作尝试。

• Trained on the same dataset as ANIMA. It still feels underfit, though, so I’ll probably keep experimenting.

• 请测试，如果有什么问题，请留言告知。Please test it and let me know in the comments if you encounter any issues.

____________________________________________________________________________________

ANIMA

V2：

• 新增了些许数据集。

• 修改了配方和使用了新的训练器，整体表现更好，指令遵从度改善，光影、画面、阴影也有一定改善。

• 解决了马赛克容易出现的问题，但由于数据集基本全是有马赛克，所以你仍然要透过提示词稍作控制。

• added a small amount of new training data.

• Updated the training settings and switched to a new trainer, resulting in better overall performance, improved prompt adherence, and noticeable improvements in lighting, image quality, and shadows.

• Fixed the issue of mosaics appearing too frequently.However, since most of the training dataset contains mosaic censorship, you'll still need to use prompts to keep it under control.

________________________________________________________________________