from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/ginger-girls-flux', weight_name='Ginger_Girls_Flux.safetensors')
image = pipeline('ginger,A photo-realistic shoot from a frontal camera angle about a gothic woman with long red hair wearing a white and black corset with a fur-lined hood, standing in a snowy outdoor setting at night. the image also shows a lamppost in the background and a dark, foggy atmosphere. on the middle of the image, a 1 woman, who appears to be a young adult, with pale skin and a serious expression, is standing. she has long, flowing red hair and is wearing black gloves, gauntlets, and a silver corset. her body is slim, and she is wearing high-leg leotard with black thigh-high stockings and gauntlets. her eyes are looking directly at the viewer, and her lips are painted with dark lipstick. she is standing with her arms at her sides, wearing a silver and black gauntlets with fur trim. the corset is detailed with intricate designs and has a belt around her waist. the background is dark and foggy, with a streetlamp visible in the distance. ').images[0]

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