









Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord
To support me you can buy me a coffe at https://ko-fi.com/antonioriolo
Recommended settings:
Make sure you are aware on the usage instructions of LORA
Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)
CFG Scale : 5 to 10
LORA weight for txt2img: reccomended 0.3-0.7.
Keys: stone_statue, on a pedestal, stone_color, sand_statue, white_statue
I made this model just for fun. It works as expected, it just makes a stone_statue out of the subject.
I have tryied to use it with other LoRAs, like clothing LoRAs and it usually works.
The training images are not only about humans (most of the posted images are), there are many about animals and fantasy stuff, so it should be able to generate a statue of everything, just give it a try maybe with a xy plot on the weights.
My advice is to always use stone_statue keyword with a good weight and use it in combo with stone_color/white_statue/sand_statue (one of these to select the color of the statue)
It should work also with anime.
Enjoy!
If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians
1. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。
2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領
