No trigger word is needed for this LoRA. Recommend LoRA strength of <code>0.8</code> for the best results.Trained on handpicked images I generated myself using Illustrious (RouWei v0.8).You should use Klein or ZIT to do an hires pass at 0.5 denoise if images look overly noisy.

Style > AgileStyle

Trained in Onetrainer using <code>Muon</code> with spectral normalization at batch size 4 for 1600 steps at 512px.This LoRA is both likely slightly over-trained, and generates grainy image (this most likely comes from the dataset too)

Files with SHA256: 38f5d6fcb56e6172bebdfb8a6b7dca6f5dff0dd3ba97add0b205ae57e92e03d5