from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('openfree/z-tao', weight_name='z-tao.safetensors')
image = pipeline('A person in a korean rich hotel Z.TAO,  pink-purple hair color, white suit best quality, real photo, 26K, Jungkook earrings').images[0]
image.save("my_image.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers