LoRA model for the AI VTuber Neuro-sama and her sister Evil Neuro, as well as #1 Tech VTuber Vedal (the turtle).
My contribution to The Swarm.
Trained on a mixture of official images, fanart, and lots and lots of VoD screencaps. May be just a bit biased towards her default pose, but you can fairly easily prompt for other things.
Recommended settings
• LoRA network weight 0.7-0.8 for Animagine XL v3, or very closely related models.
• Depending on the relation of the checkpoint, higher weight may be needed.
• Trained on Animagine XL v3. May not work well on models not closely related to Animagine XL v3.
• I highly recommend using highres fix with this LoRA, as well as quality tags such as masterpiece, best quality, etc.
• If using with other LoRA or heavy style tags, weight may need to be lowered further if it is clashing.
Suggested prompting
Neuro-sama (Cardigan)
1girl, neuro-sama, blue eyes, light brown hair, ahoge, two side up, hair ribbon, red ribbon, heart hair ornament, yellow cardigan, open cardigan, blue sailor collar, long sleeves, aqua bow, purple heart, button badge, star \(symbol\), drone, the number "1" on a badge, turtle, blue skirt, pleated skirt, asymmetrical legwear, black thighhighs, black kneehighs, bandaid on knee, brown footwear, loafers,
Evil Neuro (Cardigan)
1girl, evil neuro-sama, red eyes, light brown hair, ahoge, two side up, hair ribbon, dark red ribbon, heart hair ornament, black cardigan, open cardigan, black sailor collar, long sleeves, red bow, heart, button badge, star \(symbol\), drone, the number "1" on a badge, turtle, black skirt, pleated skirt, asymmetrical legwear, black thighhighs, black kneehighs, bandaid on knee, grey footwear, loafers,
• If you want to mount something on her head, dropping "ahoge" can help with consistency
• Her badges can be a bit inconsistent, especially the drone badge. Please adjust prompt weights and sampling method as needed.
• The legwear/bandaid often generates in the opposite configuration