Images used for training are ai-generated by me. Thus the styles can often look sloppy.
Honestly I'm not too happy with any of those, but low weight can often be good enough to steer the model towards a specific style without destroying its abilities.
For the StrongLine style, something like expressive colored manga style digital illustration with a realistic touch and extreme ink linework can help steer the model towards the intended style.
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.