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..."
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
