I put 129 images of my drawings/sketches, etc. and got this LoRA!

v3 is about correct LoRA training (civitai artstyle training with buzz). About more drawings in dataset to get more proper sketch-draw-ish style, more lookin like hand drawn picture.

Hey everyone, if you're curious about this, I totally recommend experimenting to find the result that works best for you! We’d love to see what you come up with—don’t forget to share!