Change Browsing Level to "R" if you want to see the full set of example images.
A character LoRA for the indie VTuber NekoElla. Trained on a dataset of 45 images that consists largely of cut up screenshots, images generated by ChatGPT, and a few fan arts. There are inconsistent generation issues when it comes to the cat thighhighs but oh well. The below and attached triggers are general suggestions. You can almost certainly get better and more consistent results by more specific prompting. I'm just lazy. Play around with it to see what works for you.
Detailers are highly recommended for the face and eyes.
Manual inpainting or image refinement through ChatGPT are recommended if you're looking to generate small details.
Probably won't be updated.
All example images were generated without a refiner step. You can probably make your generations look much better with improved workflows.
Triggers:
NekoElla, long hair, hair past waist, multicolored hair, light brown hair, purple hair, flower hair accessory, purple eyes, large breasts, catgirl, cat ears, white ear fluff, cat tail,
long sleeved sweater, chest cutout, dark purple sweater, dark purple thighstrap, dark purple thighhighs, cat thighhighs,


