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
FAQ
Comments (4)
Great work!
I am curious: why did you ramp it up to 20k steps?
I see your other characters, from Castlevania, worked well with 2-4k steps.
Also how many training images did you use?
Thank you
I used 131 images, which is part of the reason for the higher step count (most of my LoRAs are closer to the 15-30 image range). The other reason is that this was my first LoRA and I didn't know what I was doing :)
I need to completely redo all the captions for this one since I over-described her outfits and physicality, requiring painstaking detail in the prompt to consistently get her details right. The next version will be much better, when I can get around to it.
Any chance of getting a hunyuan version of this one? 😁 Looks amazing.
I have one but I'm not happy with it yet. Will post when I get it working well.