First training attempt!
I have pretty good success using AnythingV4 with DDIM sampler at weight 0.9.
Weight: 0.6-0.9 (you can go lower)
No inpainting used on preview images.
Used Hollowstrawberry's Data Set Maker and Lora Trainer on Google Collabs.
PROMPTS
-------------------------------------------------------------------------------------------
NEGATIVE PROMPTS: (may or may not help - depending on what you want:)
Art nouveau
2000s \(style\)
White Background
Wings
Close-up
(Artist name)
Skinny
Narrow waist
Bottomless
Topless
Torch
Border
Cropped
Monochrome
2girls/3girls/multiple girls <-- (use one or more of these if you want just one character to appear)