Best at close-up, pose will be repetitive at some seeds and prompts because its dataset have many similar pose, but it can be solved with Controlnet, the face similarity will be decrease though.
Please consider to support me by buying me some coffee so I can make a new LoRA faster. I do open commissions there too if you want to make your own custom LoRA: My BMAC page
There is v1B which is better than v1A here: v1B
Join KPOP Diffusion Discord: https://discord.gg/NrBDMX79Da
Best checkpoints/models to use:
Realistic: VisionGen, ChillOutMix, ArtEros, Deliberate, WoopWoop Photo
Fanart/painting style: Dreamshaper, LucidMix, SunshineMix
Best at close-up, pose will be repetitive at some seeds and prompts because its dataset have many similar pose, but it can be solved with Controlnet, the face similarity will be decrease though.
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
