A LoRA I made for Velma Dinkley. I used <lora:VelmaDinkley:1> for these pictures but play around with it and see how it works. It works better if you use Danbooru tags. I use the extension Booru tag autocompletion It is available in the extensions tab. This really helps do the prompting for me. I used A few different models you can check which one by looking at the photos prompts. The trigger word is just a good base prompt for getting the character. Let me know what y'all think!
I used https://civarchive.com/models/4845/sxz-bloom at .5 for all of these photos I think.
Style-Princess was made by @theally go check out her stuff it is amazing!!
Description
FAQ
Comments (1)
So I need to put all the "velma dace dinkley, 1girl, blush, breasts, brown_eyes, brown_hair, freckles, glasses, medium breasts, lips, looking_at_viewer, nose, orange_shirt, orange_sweater, short_hair, smile, sweater, turtleneck, turtleneck_sweater" or "lora:VelmaDinkley:1" will be enough? And can I add or take away some of tokens out of trigger phrase?