Hiroshi Nagai style lora for Qwen Image

This is a lora I trained for Qwen Image to be in the style of artist Hiroshi Nagai. It was trained for 3000 steps using ostris ai toolkit

For usage in ComfyUI

You can try it out with this basic ComfyUI workflow

I recommend using at least 30 steps. Attempting to use this lora with the Qwen Image lightning lora for fewer steps seemed to damage quality during testing.

Structure your prompts to trigger it like "Hiroshi Nagai style..."

image/png

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support