No trigger word needed for this lora.<hr />v2.1: Is closer to the artist style and coloring that v2 while maintaining good quality. I think I need to remove some of the image from the artist to actually get the style I want, since the quality of his works is very uneven.v2: v2 is far from perfect, but better in every single way than v1. It still hasn't learned this style perfectly and focused a bit too much on background instead of characters.

Style > Range Murata

Lora trained without triggerword.Lora trained on 80 range murata images at 768x, using kohya-ss/sd-scripts. The lora has been trained for 2.5k steps with TALON optimizer 6e-04 LR cosine batch size 4.It is trained on Chroma-DC-2K, which I feel is a better model than HD.

Files with SHA256: 88f9fc177d05499fcbc70d5580c16e9c0c817cb59721ab4f8ac365ba09680598