https://civitai.com/models/2079615/luisap-zimage-qwen-midjourney-dream?modelVersionId=2353064

The author describes a 500 to 1000 steps training

🤔 :

"this was requested, my default style loras was trained in 500 steps, but this goes beyond 1000.

no need to trigger, just prompt and go.

yeah you can mix with your model, for merge guys."

Will the exerimental realistic workflow make the job?