This LoRA of Tera is trained for the Flux Dev checkpoint. It was trained against hand-captioned HD screencaps from the Castlevania Nocturne TV series. Works for both anime/cartoon depictions as well as photorealistic. For multiple prompt examples, check my images: https://civarchive.com/user/thebollo/images. I upload all images with full metadata attached for easy import into Forge or ComfyUI.

If you want anime-like results, just use a standard prompt that mentions "Tera." If you want a photorealistic generation, add the key phrase "analog photography aesthetic."

NOTE - This was trained on images of Tera both as a human and a vampire. Use keywords "human Tera" and "vampire Tera" respectively. Add "pointed ears" and/or "fangs" if you want more vampire aesthetic.