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('masterProfessortv/mirav1', weight_name='mirav1.safetensors')
image = pipeline('MRAV1 , a female with fair skin and red wavy hair tied in a ponytail, wearing a brown cardigan, patterned shirt, gray pants, and brown shoes, in stylized The rendering is high-quality, Pixar-inspired, with smooth textures, realistic fabric detail,').images[0]
image.save("my_image.png")

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