Stable Diffusion XL (SDXL) DreamBooth Text Encoder training difference is just amazing
No After Detailer (ADetailer) used to improve face. This is raw output. As you get better raw output you will also get better ADetailer enabled output.
1st : only UNET
2nd : my best Text Encoder training
Config will be hopefully on Patreon very soon
Current config > https://www.patreon.com/posts/very-best-for-of-89213064
Current video > https://youtu.be/EEV8RPohsbw