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('ayanda13/Ruins_v1', weight_name='Ruins_v1.safetensors')
image = pipeline('Rust-eaten locomotives slump in a valley swallowed by wildflowers and thorny brambles, their shattered windows glittering like jagged teeth under a stormy violet sky. Vines snake through coal carriages, while a lone fox pauses on tracks buried under dandelions. Lightning fractures the horizon, illuminating graffiti ghosts of names long forgotten. Ruin5').images[0]
image.save("my_image.png")

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