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('life/conceptishcat', weight_name='conceptishcat.safetensors')
image = pipeline('a pencil sketch of a girl with long hair and a backpack. She has a determined expression on her face, suggesting she is ready to take on any challenge. Her hair is long and wavy, and she is wearing a backpack with a zipper closure. The sketch is done in a realistic style, with shading and highlights to give it a lifelike appearance. conceptishcat').images[0]
image.save("my_image.png")

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