This LoRA of Trevor Belmont is trained for the Flux Dev checkpoint. It was trained against hand-captioned HD screencaps from the Castlevania 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 A111 or ComfyUI.
Description
Comments (2)
I'd recommend including some non-realistic example pics, since the source isn't realistic.
Just added a couple non-realistic examples. The model is very forgiving when it comes to that; it's much harder to beat it into photorealism. If you're looking for a 1:1 reproduction of the Castlevania animated style you should be able to use the LoRA with a CFG around 3.5 and weight/strength around 1.2.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.