训练和样图生成都使用 "Anima base-v1.0" LoRA training and sample image generation based on "Anima base-v1.0"trigger word: @dksnstyle <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8ce92b3d-80aa-4016-98a3-920b839cd9ed/original=true/8ce92b3d-80aa-4016-98a3-920b839cd9ed.jpeg" />=====================<s>十张图让男人炼了一百炉 孩子们5090的电费好贵</s>v2 更少过拟合，更闪亮的裤袜，更还原风格，代价是提示词必须写得更详细V2: Less overfitting, the pantyhose look is more shiny. The cost is that the prompts must be written in more detail.触发词还是@dksnstyletrigger word: @dksnstyle一些你可能需要的提示词：shiny/see-through pantyhose/bodystocking/legwear/clothes<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8d1d9d12-19ac-461f-8d40-00dd32d85d40/original=true/8d1d9d12-19ac-461f-8d40-00dd32d85d40.jpeg" />=====================v1 trigger word: @dksnstyleIt's slightly overfitted; you could try lowering the LoRA weight or not using the trigger word.v1 有点过拟合，可以试试降低Lora权重或者不使用触发词呃啊 关注美少女(?)画师谢谢喵 <a target="_blank" rel="ugc" href="https://www.pixiv.net/users/2306287">https://www.pixiv.net/users/2306287</a>

[Anima]dk.senie Style

Files with SHA256: e126f96bbadc08b721dd298f86e23688f7b21035306f8497c598784f9e9f5049