import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("John6666/mocase-mix-prefectponyv2-sdxl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Shero448/kozue")
prompt = "<lora:Takama_Kozue-Lover-in-Law:0.8>,kozue,1girl,long hair,red hair,brown eyes,large breasts,mature female,shirt,upper body,smile,looking at viewer,indoors"
image = pipe(prompt).images[0]kozue
- Prompt
- <lora:Takama_Kozue-Lover-in-Law:0.8>,kozue,1girl,long hair,red hair,brown eyes,large breasts,mature female,shirt,upper body,smile,looking at viewer,indoors
- Negative Prompt
- 3d,censored,monochrome
Trigger words
You should use kozue to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 2
Model tree for Shero448/kozue
Base model
John6666/mocase-mix-prefectponyv2-sdxl