This LoRA was trained against hand-captioned HD screencaps from the animated Castlevania TV series. Works for both anime/cartoon depictions as well as photorealistic. For prompt examples check my images. I upload all images with full metadata attached for easy import into A111 or ComfyUI.
Description
Use at strength 8.0 - 9.0 for realism with keywords like "analog realistic. shot on film. depth of field."
This model is best for realism. It works ok for anime but since Z-image is meant for realism it's not the best choice. Use the Flux variant if your main use case anime.
FAQ
Comments (3)
What tool did you use to train this and what were the settings?
AI-Toolkit, all default settings including 3,000 steps.
Klein 9B please