LoRA for characters
Collection
アニメや漫画のキャラで LoRA を公開してます。 • 70 items • Updated
How to use BlueTriangles/SDXL_PTD_Dio with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("OnomaAIResearch/Illustrious-XL-v2.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("BlueTriangles/SDXL_PTD_Dio")
prompt = "sdxl-ptd-dio"
image = pipe(prompt).images[0]


Trained by 29 images (of person and clothes), 10 epochs, 2-10 repeats for 390 steps. Trigger and useful keywords (tags) are as follows.
Appearance: sdxl-ptd-dio, choker, yellow eyes, blonde hair, black choker, long hair, bow, ribbon, black bow, hair ribbon, black ribbon, parted bangs, hair bow, forehead, medium hair, ahoge, small breasts
Outfit: thighhighs, skirt, shoes, plaid clothes, plaid skirt, zettai ryouiki, long sleeves, black thighhighs, loafers, pleated skirt, shirt, white shirt, grey skirt, miniskirt, black vest, vest, jacket, white jacket
You should use sdxl-ptd-dio to trigger the image generation.
Download them in the Files & versions tab.
Base model
OnomaAIResearch/Illustrious-XL-v2.0