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('jschoormans/flux-ic-render', weight_name='vitualstaging.safetensors')
image = pipeline('[VIRTUALSTAGING] A before and after image of a kitchen. The same kitchen is shown before and after a complete makeover. [IMAGE1] The image showcases a dated kitchen with worn-out cabinets and appliances. The room has a small window above the sink, allowing limited natural light. The walls are covered in faded, floral wallpaper that gives the space a vintage feel. The kitchen features old-fashioned linoleum flooring in a yellow and green checkered pattern. A small table in the corner with two mismatched chairs, and a calendar hangs on one of the walls. The overall color scheme is dominated by muted earth tones, creating a somewhat dull and outdated atmosphere. [IMAGE2] The image presents a sleek, modern kitchen with state-of-the-art appliances and custom cabinetry. The once-small window has been expanded into a large bay window, flooding the space with natural light. The walls are painted in a crisp white, accented by a bold, geometric-patterned backsplash in shades of blue and gray.The kitchen now features a large center island with bar seating, perfect for casual dining or food preparation. Pendant lights hang above the island, adding both style and functionality. A smart refrigerator can be seen, along with other high-tech appliances. The overall atmosphere of the kitchen is bright, spacious, and inviting, with a modern color palette of white, gray, and blue.').images[0]
image.save("my_image.png")

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