---V1---
I trained this model with art from Dakosito on twitter,
This model works best between 0.8~1.0 but can be pushed farther for more intense effect.
Necessary Trigger Word:
DakositoStyle,
Use "realistic," as a negative for a more simple/flat look.
---V2---
Worked to make the model closer to the original artist, and removed some of the strange artifacting that was sometimes happening on the skin and clothing.
V2 is not a 100% upgrade over V1. It loses a lot detail in pursuit of the original artist's style. I personally use V1 and V2 interchangeably as needed to match the intended look and would urge you to try both as well.
0.8~1.0 is still the preferable strength.
Necessary Trigger Word:
DakositoStyle,
In testing, I think I've mostly reduced the necessity of Negatives for a decent final product, but try using "realistic" if you are still having issues.
If you like my work and want to give me some extra support, you can always tip⚡Buzz⚡to help me make more lora.