A style LoCon trained on 200 most collected pony-based images from Civitai site.BASEMODLE:Animagine3.1v1:Trained 224 images from Civitai.393 images for regularization.17 epochs × 5 repeats per epochbatch size = 12U-net lr = 8e-4te lr = 2e-4left: lora weight = 0right: lora weight = 1test ver.4:It is a little bit underfitted but still works. I found that those quality tags and authentic tags (best quality, masterpiece, very aesthetic, ...) Animagine v3.1 has been trained can change the art style generated by this checkpoint. Fixing it in the next test version.有些欠拟合但是目前是有效的。我发现Animagine v3.1自带的质量控制词和美学提示词会改变生成图片的画风，所以这个实验版本需要不填写质量词。下一版会修复。Pony Diffusion V6 XLv1:It will be improved.待改进。
