Trained on 768
Dataset sorted out
Better tagging
Is now more accurate








Rikku FFX & FFX-2 | Character LoRA
V3:
Now trained properly, finally.
Weight can go from 0.8 up to 1. I recommend 1. Works with almost every Style, every Character and Photorealistic Models.
Trigger Words:
XOutfit: RikkuX, x hair ornament, goggles around neck, fingerless gloves, midriff, navel, belt, boots
X2Outfit: RikkuX2, blue headband, yellow ??????, scarf, skirt, navel, detached sleeves, ?????? top only
Other Outfits:RikkuX, x hair ornament or RikkuX2, blue headband
V2:
Rikku | FFX & FFX-2
I recommend 0.7-1. ControlNet will streamline full body shots much easier, or more complex poses. Works with almost every Style, every alternative Outfit, Photorealistic Models and ???? LoRA's. Be warned that despite some SFW gens here, this LoRA is ????-happy and will often give you a mostly ???? Rikku unprompted. You can generate both Outfits (from FFX and FFX-2). See description below.
V2: Updated Dataset and fixed tags. Use RikkuX or RikkuX2 for her Outfit and Rikku for every other costum Outfit.
Trigger Word:
Rikku
Helping Prompt:
blonde hair
X Outfit:
RikkuX
X-2 Outfit:
RikkuX2, ??????, shorts, scarf, headband
V1:
Trigger Word:
Rikku
Helping Prompt:
1girl, solo, long hair, ???????, blonde hair, hair ornament, ??????????????, green eyes
X Outfit:
gloves, navel, braid, boots, shorts, hairclip, fingerless gloves, scarf, x hair ornament, goggles, goggles on head
X-2 Outfit:
swimsuit, braid, ??????, detached sleeves, scarf, headband, ?????? top only, zoom layer, yellow ??????, blue headband
How to use LoRA's in auto1111:
Download LoRA
Copy the file to stable-diffusion-webui/models/lora
Select your LoRA and use the triggerword
Make sure to change the weight if needed (by default it's :1)
Have Fun!
Trained on 768
Dataset sorted out
Better tagging
Is now more accurate
1. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。
2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領
