在SDXL1.0模型训练的，因此泛化较好，适配与不同的SDXL微调模型，权重建议0.6到0.8左右。采样器推荐 euler a,dpm+2msde karras,3m采样器不推荐，
尺寸大小建议1600X900，步数20到30步，没有测试太多，因为我这台电脑跑xyz图，有点太吃力了。
可以用，raw photo，黄昏，雾气弥漫，宏伟的建筑，城市街道，
触发词是这个，potala palace
Run5
Version Detail
SDXL 1.0
30
20
Project Permissions
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated images
Use on generation services
Sell this model or merges
Commercial Use
Comments
Related Posts
No posts yet
Describe the image you want to generate, then press Enter to send.