No trigger word is needed for this LoRA. Recommend LoRA strength of 0.8 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.
Description
No trigger word is needed for this LoRA. Recommend LoRA strength of 0.8 for the best results.
Trained on 300 handpicked images I generated myself using Illustrious (RouWei v0.8).
V2 was trained in Onetrainer using Prodigy Plus Schedule Free at batch size 8 for 1750 steps at 512, 768, 1024px
This LoRA is both under-trained (ran out of runpod money), and over-fitted since my dataset is too repetitive, it is a good first test, but I will definitely do another version once I have a less repetitive set of images.
Captioning was done using Gemini 3 Flash.