Trained a lora similar to Illustrious/NoobAI styles. Model itself has a great anime capabilities but mostly it will generate like an anime screencap. This lora help achieving more illustration-like style.
Recommended strength: 0.8-1.3
Trigger word:
elusarca anime style
Recommended prompt prefixes that works well wit Z-Image:
high-quality anime illustration, 2D, clean lineart, cel-shaded, vibrant colors, soft shading
Trained with AI Toolkit by Ostris
Description
FAQ
Comments (3)
What kind of Lazy Embeddings are used?
I used the embeddings I found here called lazy embeddings,not when training, but when generating these sample images.
Beautiful LORA! Thank you very much! it's get great images! Please don't leave her.