Latest version is a complete overhaul. wd tagging, better image selection.
Trained on picXreal, but it works on many modern models.
Keep prompts simple. Start with positive prompt as "pmbsly, photograph, ..." and negative as ONLY: "bad proportions" it's a bit sensitive to too much negative prompting.
Description
more training, turned out better for portraits but less versatile
FAQ
Comments (4)
524568Jul 7, 2023· 6 reactions
CivitAI
evil thoughts forming
Wow, so much better that V1. Thanks a lot mate 👍.
Got the best results with a weight of 0.8
Very strange, I could not get this Lora to work. The images were terrible.