The previous version had a broken clip encoder. This version fixes that issue. The model becomes more stable, but no other major changes.




This is the blend I've been using for a while to generate some pics. It was born from my love of the skin textures and photorealistic look in Dreamlike Photoreal and my hate of how difficult it was to pose people in unorthodox ways. This merge tries to reach a good compromise, keeping skin textures and photo realistic capabilities while adding a ton of artistic and posing components, as well as some capability of understanding danbooru tags.
It's capable of some hardcore, but not the focus of the model at all, and therefore it's very hard to prompt.
The blend includes Dreamlike Photoreal, so here's the license. You have to follow it.
The previous version had a broken clip encoder. This version fixes that issue. The model becomes more stable, but no other major changes.
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
