As usual tried to recreate uodenim's style with a VERY SLOW cook with the intent of allowing expressions already present in the checkpoints without too much bleeding from the ones in the dataset, I think this LoRA manages that decently well allowing for a bit more of creative freedom without external LoRAs or LECOs, while also taking other LoRAs and LECOs without much issue, weights go from 0.65 to 1
Trained for 190 epochs with 219 images at 768x768 resolution, for a total of 50160 global steps.
All preview images have Hires and Adetailer, LoRA likes VectorScope for increase saturation, reduced brightness and increased contrast due to how the artist uses color.
Any and all reviews are very much appreciated so I can know what to improve for this LoRA or for other models, thank you~