用的1024*1536的图集训练的,显卡顶不住训练的次数没有很多,后期会继续优化的。权重0.7到0.9,CFG为6、步数20到30即可,使用高分辨率修复效果会比较好。可用ADetailer修复脸部。示例图有一张是高分修复未加AD修脸,一张是没有高分修复加了AD修炼,可看出区别。出图底膜用的是magicmix realities v5。测试用的vae是pastel-waifu- diffusion.vae.pt
Run7
Version Detail
SD 1.5
10
10
用的1024*1536的图集训练的,显卡顶不住训练的次数没有很多,后期会继续优化的。权重0.7到0.9,CFG为6、步数20到30即可,使用高分辨率修复效果会比较好。可用ADetailer修复脸部。示例图有一张是高分修复未加AD修脸,一张是没有高分修复加了AD修炼,可看出区别。出图底膜用的是magicmix realities v5。测试用的vae是pastel-waifu- diffusion.vae.pt
Project Permissions
Use in TENSOR GREEN Online
As a online training base model on TENSOR GREEN
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
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.