V2 has improved generalization, but there are also some small issues, so I suggest also taking a look at V1
Suggested prompt:wgz style,portrait of a beautiful women highly detailed
Do not use SD 1.5 prompts , Just enter a few words you want
The DLC for 2077 is coming soon, so I made some cyberpunk imgs to test generalization
Suggest to use the Unipc sampler ,Euler a is good too.
Training is focus on face. and might be a slight overfitting.
The most imges are 1024 reslution output.
Some images (no gennerate data )have been improved by using PS and img 2img.