import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("John6666/prefect-illustrious-xl-v15-sdxl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Shero448/kaede")
prompt = "lazypos, <lora:Kaede_Hijikata-Erotical_Wizard_to_12-nin_no_Hanayome-IL:0.8> ,1girl,solo,mm,monochrome,greyscale,ponytail,hair ribbon,huge breasts,"
image = pipe(prompt).images[0]kaede
- Prompt
- lazypos, <lora:Kaede_Hijikata-Erotical_Wizard_to_12-nin_no_Hanayome-IL:0.8> ,1girl,solo,mm,monochrome,greyscale,ponytail,hair ribbon,huge breasts,
- Negative Prompt
- lazyneg,lazyhand,speech bubble, old man, loli,extra digits,bad hands, censored,
Trigger words
You should use 1girl to trigger the image generation.
You should use solo to trigger the image generation.
You should use mm to trigger the image generation.
You should use monochrome to trigger the image generation.
You should use greyscale to trigger the image generation.
You should use ponytail to trigger the image generation.
You should use hair ribbon to trigger the image generation.
You should use long hair to trigger the image generation.
You should use huge breasts to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for Shero448/kaede
Base model
KBlueLeaf/kohaku-xl-beta5 Finetuned
John6666/prefect-illustrious-xl-v15-sdxl