VRChat Hakka

基于animagineXLV3_v30训练，生成Booth上售卖的3D模型Hakka图像。

推荐权重：推荐1。

数据集以1152*1152分辨率进行训练，有48张。

触发词：vrchat hakkka，如果想要强化引导默认的衣服就再加上vrchat hakkka default

我没有办法再缩小文件大小的情况下保持质量，也许会更新一版20mb的降质版模型。

Based on the training of animagineXLV3_v30, a 3D model of Hakka is generated for sale on Booth.

Recommendation Weight: 1

The dataset is trained at a resolution of 1152x1152 and consists of 48 images.

Trigger word: vrchat hakkka. If you want to reinforce default clothing guidance, add vrchat hakkka default.

I'm unable to maintain quality while further reducing file size. Perhaps I'll release a degraded version of the model around 20MB in the future.