11/24 Update:version for illustrious XL based model is available now.Trigger Words:<pre><code>alp</code></pre><hr />4/2 Update:new Locon version available now.Trained on animagineXLV3.1weight around 0.8 ~ 1.0 works just finestabler and much smaller in size.<hr />Trained on animagineXLV3weight around 0.8 ~ 1.0 works just fineMight increase mistakes in drawing hands, but I think it's acceptable.Train with this free colab notebook:<a target="_blank" rel="ugc" href="https://github.com/Linaqruf/kohya-trainer/blob/main/kohya-LoRA-trainer-XL.ipynb">kohya-trainer/kohya-LoRA-trainer-XL.ipynb at main · Linaqruf/kohya-trainer · GitHub</a>with almost conpletely default setting, in free tier<hr />底模为 animagineXLV3权重0.8~1.0左右都很好使用之后有可能画手会更容易出错但是体感还好，所以凑合用吧（使用的以下colab脚本：<a target="_blank" rel="ugc" href="https://github.com/Linaqruf/kohya-trainer/blob/main/kohya-LoRA-trainer-XL.ipynb">kohya-trainer/kohya-LoRA-trainer-XL.ipynb at main · Linaqruf/kohya-trainer · GitHub</a>几乎全用的默认参数，免费用户也可以白嫖

Alp Style SDXL / illustrious XL

Lora version trained on Animagine V3.0

Files with SHA256: 545d7b85ad1fb978d1e6f5cfab119d360f80d24378ac9498dd0f4fce38effb88