import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("MarkBW/sarang-xl")
prompt = "sarang, <lora:sarang-XL:1.1>a woman wearing Cardigan and relaxed-fit jeans, busy street, smiling"
image = pipe(prompt).images[0]sarang-xl
- Prompt
- sarang, <lora:sarang-XL:1.1>a woman wearing Cardigan and relaxed-fit jeans, busy street, smiling
- Negative Prompt
- Bad quality, black and white, dark, 3d, people, caucasian
Model description
Creates the likeness of a K-Pop singer. Use your favorite realistic model and keep your weight between 0.8 and 1.0
Trigger words
You should use sarang 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
- 3
Model tree for MarkBW/sarang-xl
Base model
stabilityai/stable-diffusion-xl-base-1.0