甘宁模型优化:

1.精简触发词，特征更稳定(默认还原红色眼睛)

2.提高兼容性，可以搭配更多lora使用

3.甘宁现在可以自由搭配衣服了

4.模型从lora变换成lycoris

5.使用权重：0.8-1

Gunning model optimization:

1. Simplified trigger words, more stable features (default restore red eyes)

2. Improve compatibility, can be used with more lora

3. Ganning is now free to match her outfits

4. The model is transformed from lora to lycoris

5. Use weight: 0.8-1

接角色训练，根据模型难度决定（88r起步包修改，搜集素材20r）。

感谢打赏的朋友，QQ：3250911131，

Donate a cup of coffee: https://ko-fi.com/timoplay

Donate electricity AFDIAN（爱发电）：https://afdian.net/a/timoplay

Donate a certain amount of coffee and I will make a lora for you (need to bring your own materials)。Discord：timoplay

三幻甘宁模型，本模型持续优化更新，收藏以便第一时间体验更新，触发词请务必打上，请勿商用！(最后更新时间：2023/7/15)

三幻孙策模型：https://civitai.com/models/40902/sunce

v2更新：训练方法优化，降低了头巾的绑定性，提高了还原性。推荐权重0.9以下，重绘幅度应该低于0.3.

v2 update: The training method is optimized, the binding of the headscarf is reduced, and the reduction is improved. The recommended weight is below 0.9, and the redrawing range should be below 0.3.

主模型推荐：model（模型）：https://civitai.com/models/44036/boxmix-25dmale-enhancement

For the Sanhuan Ganning model, because there are too few training materials, it will cause Xiemei to open her mouth and bind her turban. The turban can be removed through layered control. Opening her mouth can only draw cards at present, and the weight should not be higher than 0.75.Be sure to type in the trigger words!

Sanhuan Ganning モデルの場合、トレーニング用の資料が少なすぎるため、Xiemei が口を開いてターバンを結びます.ターバンはレイヤード コントロールを使用して取り外すことができます.彼女の口を開くと、現在カードを引くことしかできません。 0.75 を超えてはなりません。必ずトリガーワードを入力してください！

Sanhuan Ganning 모델의 경우 교육 자료가 너무 적기 때문에 Xiemei가 입을 벌리고 터번을 묶을 수 있습니다.터번은 레이어드 제어를 통해 제거할 수 있습니다.입을 열면 현재 카드를 뽑을 수만 있으며 무게는 0.75보다 높지 않아야 합니다.트리거 단어를 입력하십시오!