Future present and all those things. Ghostly, cyberpunk, teal/purple/pink colors. Has regularized out a lot, so you will need to prompt in the style you want.
in 80s anime style
in comic book style
Colors of clothing, hair, eyes will need to be in the prompt to get more consistent results.
Works great with a VAE. kohya-ss Lora, so best if used with Additional Networks extension. Excited to see what you come up with.
Trained using D-Adaptation at 1.0 Unet and 0.5 Text Encoder. 200 training images. "a anime" Regularization images (does this help make the style more flexible?). Noise offset: -0.1. Straight booru captions, no trigger words.
More steps possible in the future to further increase the quality and add in more ghostly figures.
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.