from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Norod78/sd15-megaphone-lora', weight_name='SD15-Megaphone-LoRA.safetensors')
image = pipeline('A scary sea monster is talking holding a megaphone in its tentacle during a storm  , Very detailed, clean, high quality, sharp image').images[0]

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