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('sharaku/dantat-v1', weight_name='dantat-v1.safetensors')
image = pipeline('DANTAT a photo of a man and woman standing next to each other at the beach with a very sunny say and the ocean in the background bokeh effect, sunset').images[0]
image.save("my_image.png")

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