Qwen:
Trained with Ostris Toolkit: Dataset is 44 images (mainly from "Monster", "20th Century Boys" and "Pluto" by Naoki Urasawa) with no trigger word (but sometimes it helps to add "black and white manga style image of").
All the image have been generated in 4 steps in addition to the lightning lora by lightx2v
The prompt adherence of Qwen is really impressive, but I feel like the likeness of the style is not as good as with Flux (even tho is still good), but I'm still experimenting so it's just an early opinion.
Flux:
Trained on images from the manga "Monster" and "20th Century boys" by Naoki Urasawa.
Start the prompt with :
A naoUrasawa style image of
Using this upscaler seems to improve the style towards a true manga scan most of the time (and get rid of colors). I've used it with hires fix and denoising strenght of 0.5.