✨ Hello everyone! Welcome to another one of my LoRAs.
She's one of the 52 'workers' at the Succubus Cafe.
I made this LoRA with one hand, from just 1 image or the few references I could extract from the anime. :3
🗒️ Other resources
👉Project Changelog & Updates
đź’¬ Suggest a Character
Have a favorite character? You can suggest it here. I review all proposals!
(But I can't promise to make them all :))
👉Suggestions
🎯 Commission ?
Of course you can requests any type of character or custom styles, contact me through:
Discord (Soon)
Recommended Settings:
Sampler: Euler or DPM++ 2M (25–35 steps)
LoRA Weight: 0.9 (up to 1.0 for higher accuracy)
ADetailer: Enabled
CFG Scale: 5-7
Thank you for your support! Every download, comment, or Buzz⚡ helps me keep creating.
Enjoy generating with this LoRA!
Description
🧬Physical characteristics
020ka_cnr, 1girl, long hair, large breasts, pointy ears, orange hair, brown eyes, twintails, hair ribbon
đź‘— Outfit
elbow gloves, aid headdress, choker, purple bikini, purple gloves, bare shoulders, high heels, frilled thighhighs, lowleg panties
FAQ
Comments (4)
Thanks for sharing all these loras. What happened to 007?
That’s a lot of work with just one or a few reference images. What do you use to get more illustrations of these characters? Something that uses the base image as a reference?
Nope. I only use the original image, without creating other variations with AI, img2img, inpainting, etc...
What I do is an interpolation between 2 datasets — that way I take the character's features and insert them into a second varied dataset.
This is done with vectors of course, during training. But basically that's what happens.
I developed the method myself :3. I don't know if there are other ways. But this works for me. ^^
@Cinabrio Do you teach the method anywhere?